Daily Papers

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, is it possible to use few-shot demonstrations to efficiently jailbreak LLMs within limited context sizes? While the vanilla few-shot jailbreaking may be inefficient, we propose improved techniques such as injecting special system tokens like [/INST] and employing demo-level random search from a collected demo pool. These simple techniques result in surprisingly effective jailbreaking against aligned LLMs (even with advanced defenses). For examples, our method achieves >80% (mostly >95%) ASRs on Llama-2-7B and Llama-3-8B without multiple restarts, even if the models are enhanced by strong defenses such as perplexity detection and/or SmoothLLM, which is challenging for suffix-based jailbreaking. In addition, we conduct comprehensive and elaborate (e.g., making sure to use correct system prompts) evaluations against other aligned LLMs and advanced defenses, where our method consistently achieves nearly 100% ASRs. Our code is available at https://github.com/sail-sg/I-FSJ.

Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs' safety alignment via fine-tuning stand out due to its stable jailbreak performance. In particular, a recent study indicates that fine-tuning with as few as 10 harmful question-answer (QA) pairs can lead to successful jailbreaking across various harmful questions. However, such malicious fine-tuning attacks are readily detectable and hence thwarted by moderation models. In this paper, we demonstrate that LLMs can be jailbroken by fine-tuning with only 10 benign QA pairs; our attack exploits the increased sensitivity of LLMs to fine-tuning data after being overfitted. Specifically, our fine-tuning process starts with overfitting an LLM via fine-tuning with benign QA pairs involving identical refusal answers. Further fine-tuning is then performed with standard benign answers, causing the overfitted LLM to forget the refusal attitude and thus provide compliant answers regardless of the harmfulness of a question. We implement our attack on the ten LLMs and compare it with five existing baselines. Experiments demonstrate that our method achieves significant advantages in both attack effectiveness and attack stealth. Our findings expose previously unreported security vulnerabilities in current LLMs and provide a new perspective on understanding how LLMs' security is compromised, even with benign fine-tuning. Our code is available at https://github.com/ZHIXINXIE/tenBenign.

Large Language Models (LLMs) face increasing threats from jailbreak attacks that bypass safety alignment. While prompt-based defenses such as Role-Oriented Prompts (RoP) and Task-Oriented Prompts (ToP) have shown effectiveness, the role of few-shot demonstrations in these defense strategies remains unclear. Prior work suggests that few-shot examples may compromise safety, but lacks investigation into how few-shot interacts with different system prompt strategies. In this paper, we conduct a comprehensive evaluation on multiple mainstream LLMs across four safety benchmarks (AdvBench, HarmBench, SG-Bench, XSTest) using six jailbreak attack methods. Our key finding reveals that few-shot demonstrations produce opposite effects on RoP and ToP: few-shot enhances RoP's safety rate by up to 4.5% through reinforcing role identity, while it degrades ToP's effectiveness by up to 21.2% through distracting attention from task instructions. Based on these findings, we provide practical recommendations for deploying prompt-based defenses in real-world LLM applications.

Although significant efforts have been dedicated to aligning large language models (LLMs), red-teaming reports suggest that these carefully aligned LLMs could still be jailbroken through adversarial prompts, tuning, or decoding. Upon examining the jailbreaking vulnerability of aligned LLMs, we observe that the decoding distributions of jailbroken and aligned models differ only in the initial generations. This observation motivates us to propose the weak-to-strong jailbreaking attack, where adversaries can utilize smaller unsafe/aligned LLMs (e.g., 7B) to guide jailbreaking against significantly larger aligned LLMs (e.g., 70B). To jailbreak, one only needs to additionally decode two smaller LLMs once, which involves minimal computation and latency compared to decoding the larger LLMs. The efficacy of this attack is demonstrated through experiments conducted on five models from three different organizations. Our study reveals a previously unnoticed yet efficient way of jailbreaking, exposing an urgent safety issue that needs to be considered when aligning LLMs. As an initial attempt, we propose a defense strategy to protect against such attacks, but creating more advanced defenses remains challenging. The code for replicating the method is available at https://github.com/XuandongZhao/weak-to-strong

Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or unreadable inputs and exhibit poor transferability, while prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity. We propose a concise and effective two-stage framework that combines the advantages of these approaches. The first stage performs a scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent. The second stage then utilizes information from the model's hidden states to guide fine-grained edits, effectively steering the model's internal representation of the input from a malicious toward a benign one. Extensive experiments demonstrate that this method achieves state-of-the-art Attack Success Rate, with gains of up to 37.74% over the strongest baseline, and exhibits excellent transferability to black-box models. Our analysis further demonstrates that AGILE maintains substantial effectiveness against prominent defense mechanisms, highlighting the limitations of current safeguards and providing valuable insights for future defense development. Our code is available at https://github.com/yunsaijc/AGILE.

As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method has yet achieved complete invulnerability to attacks. We propose an alternative approach: instead of seeking perfect adversarial robustness, we develop rapid response techniques to look to block whole classes of jailbreaks after observing only a handful of attacks. To study this setting, we develop RapidResponseBench, a benchmark that measures a defense's robustness against various jailbreak strategies after adapting to a few observed examples. We evaluate five rapid response methods, all of which use jailbreak proliferation, where we automatically generate additional jailbreaks similar to the examples observed. Our strongest method, which fine-tunes an input classifier to block proliferated jailbreaks, reduces attack success rate by a factor greater than 240 on an in-distribution set of jailbreaks and a factor greater than 15 on an out-of-distribution set, having observed just one example of each jailbreaking strategy. Moreover, further studies suggest that the quality of proliferation model and number of proliferated examples play an key role in the effectiveness of this defense. Overall, our results highlight the potential of responding rapidly to novel jailbreaks to limit LLM misuse.

Despite rich safety alignment strategies, large language models (LLMs) remain highly susceptible to jailbreak attacks, which compromise safety guardrails and pose serious security risks. Existing detection methods mainly detect jailbreak status relying on jailbreak templates present in the training data. However, few studies address the more realistic and challenging zero-shot jailbreak detection setting, where no jailbreak templates are available during training. This setting better reflects real-world scenarios where new attacks continually emerge and evolve. To address this challenge, we propose a layer-wise, module-wise, and token-wise amplification framework that progressively magnifies internal feature discrepancies between benign and jailbreak prompts. We uncover safety-relevant layers, identify specific modules that inherently encode zero-shot discriminative signals, and localize informative safety tokens. Building upon these insights, we introduce ALERT (Amplification-based Jailbreak Detector), an efficient and effective zero-shot jailbreak detector that introduces two independent yet complementary classifiers on amplified representations. Extensive experiments on three safety benchmarks demonstrate that ALERT achieves consistently strong zero-shot detection performance. Specifically, (i) across all datasets and attack strategies, ALERT reliably ranks among the top two methods, and (ii) it outperforms the second-best baseline by at least 10% in average Accuracy and F1-score, and sometimes by up to 40%.

Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of threats. Among them, jailbreak attacks that induce toxic responses through jailbreak prompts have raised critical safety concerns. To identify these threats, a growing number of red teaming approaches simulate potential adversarial scenarios by crafting jailbreak prompts to test the target LLM. However, existing red teaming methods do not consider the unique vulnerabilities of LLM in different scenarios, making it difficult to adjust the jailbreak prompts to find context-specific vulnerabilities. Meanwhile, these methods are limited to refining jailbreak templates using a few mutation operations, lacking the automation and scalability to adapt to different scenarios. To enable context-aware and efficient red teaming, we abstract and model existing attacks into a coherent concept called "jailbreak strategy" and propose a multi-agent LLM system named RedAgent that leverages these strategies to generate context-aware jailbreak prompts. By self-reflecting on contextual feedback in an additional memory buffer, RedAgent continuously learns how to leverage these strategies to achieve effective jailbreaks in specific contexts. Extensive experiments demonstrate that our system can jailbreak most black-box LLMs in just five queries, improving the efficiency of existing red teaming methods by two times. Additionally, RedAgent can jailbreak customized LLM applications more efficiently. By generating context-aware jailbreak prompts towards applications on GPTs, we discover 60 severe vulnerabilities of these real-world applications with only two queries per vulnerability. We have reported all found issues and communicated with OpenAI and Meta for bug fixes.

Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods either rely heavily on manually crafted templates, which pose challenges in scalability and adaptability, or struggle to generate semantically coherent prompts, making them easy to detect. Additionally, most existing approaches involve lengthy prompts, leading to higher query costs.In this paper, to remedy these challenges, we introduce a novel jailbreaking attack framework, which is an automated, black-box jailbreaking attack framework that adapts the black-box fuzz testing approach with a series of customized designs. Instead of relying on manually crafted templates, our method starts with an empty seed pool, removing the need to search for any related jailbreaking templates. We also develop three novel question-dependent mutation strategies using an LLM helper to generate prompts that maintain semantic coherence while significantly reducing their length. Additionally, we implement a two-level judge module to accurately detect genuine successful jailbreaks. We evaluated our method on 7 representative LLMs and compared it with 5 state-of-the-art jailbreaking attack strategies. For proprietary LLM APIs, such as GPT-3.5 turbo, GPT-4, and Gemini-Pro, our method achieves attack success rates of over 90%,80% and 74%, respectively, exceeding existing baselines by more than 60%. Additionally, our method can maintain high semantic coherence while significantly reducing the length of jailbreak prompts. When targeting GPT-4, our method can achieve over 78% attack success rate even with 100 tokens. Moreover, our method demonstrates transferability and is robust to state-of-the-art defenses. We will open-source our codes upon publication.

As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak oracle problem: given a model, prompt, and decoding strategy, determine whether a jailbreak response can be generated with likelihood exceeding a specified threshold. This formalization enables a principled study of jailbreak vulnerabilities. Answering the jailbreak oracle problem poses significant computational challenges -- the search space grows exponentially with the length of the response tokens. We present Boa, the first efficient algorithm for solving the jailbreak oracle problem. Boa employs a three-phase search strategy: (1) constructing block lists to identify refusal patterns, (2) breadth-first sampling to identify easily accessible jailbreaks, and (3) depth-first priority search guided by fine-grained safety scores to systematically explore promising low-probability paths. Boa enables rigorous security assessments including systematic defense evaluation, standardized comparison of red team attacks, and model certification under extreme adversarial conditions.

Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among various jailbreak methods, there is no standard implementation framework available for the community, which limits comprehensive security evaluations. This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs. It builds jailbreak attacks using four components: Selector, Mutator, Constraint, and Evaluator. This modular framework enables researchers to easily construct attacks from combinations of novel and existing components. So far, EasyJailbreak supports 11 distinct jailbreak methods and facilitates the security validation of a broad spectrum of LLMs. Our validation across 10 distinct LLMs reveals a significant vulnerability, with an average breach probability of 60% under various jailbreaking attacks. Notably, even advanced models like GPT-3.5-Turbo and GPT-4 exhibit average Attack Success Rates (ASR) of 57% and 33%, respectively. We have released a wealth of resources for researchers, including a web platform, PyPI published package, screencast video, and experimental outputs.

The rise of large language models (LLMs) has drawn attention to the existence of "jailbreaks" that allow the models to be used maliciously. However, there is no standard benchmark for measuring the severity of a jailbreak, leaving authors of jailbreak papers to create their own. We show that these benchmarks often include vague or unanswerable questions and use grading criteria that are biased towards overestimating the misuse potential of low-quality model responses. Some jailbreak techniques make the problem worse by decreasing the quality of model responses even on benign questions: we show that several jailbreaking techniques substantially reduce the zero-shot performance of GPT-4 on MMLU. Jailbreaks can also make it harder to elicit harmful responses from an "uncensored" open-source model. We present a new benchmark, StrongREJECT, which better discriminates between effective and ineffective jailbreaks by using a higher-quality question set and a more accurate response grading algorithm. We show that our new grading scheme better accords with human judgment of response quality and overall jailbreak effectiveness, especially on the sort of low-quality responses that contribute the most to over-estimation of jailbreak performance on existing benchmarks. We release our code and data at https://github.com/alexandrasouly/strongreject.

As Large Language Models (LLMs) are widely applied in various domains, the safety of LLMs is increasingly attracting attention to avoid their powerful capabilities being misused. Existing jailbreak methods create a forced instruction-following scenario, or search adversarial prompts with prefix or suffix tokens to achieve a specific representation manually or automatically. However, they suffer from low efficiency and explicit jailbreak patterns, far from the real deployment of mass attacks to LLMs. In this paper, we point out that simply rewriting the original instruction can achieve a jailbreak, and we find that this rewriting approach is learnable and transferable. We propose the Rewrite to Jailbreak (R2J) approach, a transferable black-box jailbreak method to attack LLMs by iteratively exploring the weakness of the LLMs and automatically improving the attacking strategy. The jailbreak is more efficient and hard to identify since no additional features are introduced. Extensive experiments and analysis demonstrate the effectiveness of R2J, and we find that the jailbreak is also transferable to multiple datasets and various types of models with only a few queries. We hope our work motivates further investigation of LLM safety. The code can be found at https://github.com/ythuang02/R2J/.

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful outputs. Existing jailbreak strategies mainly focus on maximizing attack success rate (ASR), frequently neglecting other critical factors, including the relevance of the jailbreak response to the query and the level of stealthiness. This narrow focus on single objectives can result in ineffective attacks that either lack contextual relevance or are easily recognizable. In this work, we introduce BlackDAN, an innovative black-box attack framework with multi-objective optimization, aiming to generate high-quality prompts that effectively facilitate jailbreaking while maintaining contextual relevance and minimizing detectability. BlackDAN leverages Multiobjective Evolutionary Algorithms (MOEAs), specifically the NSGA-II algorithm, to optimize jailbreaks across multiple objectives including ASR, stealthiness, and semantic relevance. By integrating mechanisms like mutation, crossover, and Pareto-dominance, BlackDAN provides a transparent and interpretable process for generating jailbreaks. Furthermore, the framework allows customization based on user preferences, enabling the selection of prompts that balance harmfulness, relevance, and other factors. Experimental results demonstrate that BlackDAN outperforms traditional single-objective methods, yielding higher success rates and improved robustness across various LLMs and multimodal LLMs, while ensuring jailbreak responses are both relevant and less detectable.

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we introduce a dataset of jailbreaks where each example can be input in both a single or a multi-turn format. We show that while equivalent in content, they are not equivalent in jailbreak success: defending against one structure does not guarantee defense against the other. Similarly, LLM-based filter guardrails also perform differently depending on not just the input content but the input structure. Thus, vulnerabilities of frontier models should be studied in both single and multi-turn settings; this dataset provides a tool to do so.

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indirect and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delays to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM as a defense instance (in detection state) to concurrently protect the target LLM instance (in normal answering state) in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs can identify harmful prompts or intentions in user queries, which we empirically validate using mainstream GPT-3.5/4 models against major jailbreak attacks. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. When deployed to protect GPT-3.5/4, Claude, Llama-2-7b/13b, and Mistral, these models outperform seven state-of-the-art defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. Further experiments show that the tuned models are robust to adaptive jailbreaks and prompt injections.

We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with a combination of augmentations - such as random shuffling or capitalization for textual prompts - until a harmful response is elicited. We find that BoN Jailbreaking achieves high attack success rates (ASRs) on closed-source language models, such as 89% on GPT-4o and 78% on Claude 3.5 Sonnet when sampling 10,000 augmented prompts. Further, it is similarly effective at circumventing state-of-the-art open-source defenses like circuit breakers. BoN also seamlessly extends to other modalities: it jailbreaks vision language models (VLMs) such as GPT-4o and audio language models (ALMs) like Gemini 1.5 Pro, using modality-specific augmentations. BoN reliably improves when we sample more augmented prompts. Across all modalities, ASR, as a function of the number of samples (N), empirically follows power-law-like behavior for many orders of magnitude. BoN Jailbreaking can also be composed with other black-box algorithms for even more effective attacks - combining BoN with an optimized prefix attack achieves up to a 35% increase in ASR. Overall, our work indicates that, despite their capability, language models are sensitive to seemingly innocuous changes to inputs, which attackers can exploit across modalities.

Jailbreaking methods for large language models (LLMs) have gained increasing attention for building safe and responsible AI systems. After analyzing 35 jailbreak methods across six categories, we find that existing benchmarks, relying on universal LLM-based or keyword-matching scores, lack case-specific criteria, leading to conflicting results. In this paper, we introduce a more robust evaluation framework for jailbreak methods, with a curated harmful question dataset, detailed case-by-case evaluation guidelines, and a scoring system equipped with these guidelines. Our experiments show that existing jailbreak methods exhibit better discrimination when evaluated using our benchmark. Some jailbreak methods that claim to achieve over 90% attack success rate (ASR) on other benchmarks only reach a maximum of 30.2% on our benchmark, providing a higher ceiling for more advanced jailbreak research; furthermore, using our scoring system reduces the variance of disagreements between different evaluator LLMs by up to 76.33%. This demonstrates its ability to provide more fair and stable evaluation.

Despite extensive safety enhancements in large language models (LLMs), multi-turn "jailbreak" conversations crafted by skilled human adversaries can still breach even the most sophisticated guardrails. However, these multi-turn attacks demand considerable manual effort, limiting their scalability. In this work, we introduce a novel approach called Multi-turn-to-Single-turn (M2S) that systematically converts multi-turn jailbreak prompts into single-turn attacks. Specifically, we propose three conversion strategies - Hyphenize, Numberize, and Pythonize - each preserving sequential context yet packaging it in a single query. Our experiments on the Multi-turn Human Jailbreak (MHJ) dataset show that M2S often increases or maintains high Attack Success Rates (ASRs) compared to original multi-turn conversations. Notably, using a StrongREJECT-based evaluation of harmfulness, M2S achieves up to 95.9% ASR on Mistral-7B and outperforms original multi-turn prompts by as much as 17.5% in absolute improvement on GPT-4o. Further analysis reveals that certain adversarial tactics, when consolidated into a single prompt, exploit structural formatting cues to evade standard policy checks. These findings underscore that single-turn attacks - despite being simpler and cheaper to conduct - can be just as potent, if not more, than their multi-turn counterparts. Our findings underscore the urgent need to reevaluate and reinforce LLM safety strategies, given how adversarial queries can be compacted into a single prompt while still retaining sufficient complexity to bypass existing safety measures.

Large Language Models (LLMs) have risen significantly in popularity and are increasingly being adopted across multiple applications. These LLMs are heavily aligned to resist engaging in illegal or unethical topics as a means to avoid contributing to responsible AI harms. However, a recent line of attacks, known as jailbreaks, seek to overcome this alignment. Intuitively, jailbreak attacks aim to narrow the gap between what the model can do and what it is willing to do. In this paper, we introduce a novel jailbreak attack called Crescendo. Unlike existing jailbreak methods, Crescendo is a simple multi-turn jailbreak that interacts with the model in a seemingly benign manner. It begins with a general prompt or question about the task at hand and then gradually escalates the dialogue by referencing the model's replies progressively leading to a successful jailbreak. We evaluate Crescendo on various public systems, including ChatGPT, Gemini Pro, Gemini-Ultra, LlaMA-2 70b and LlaMA-3 70b Chat, and Anthropic Chat. Our results demonstrate the strong efficacy of Crescendo, with it achieving high attack success rates across all evaluated models and tasks. Furthermore, we present Crescendomation, a tool that automates the Crescendo attack and demonstrate its efficacy against state-of-the-art models through our evaluations. Crescendomation surpasses other state-of-the-art jailbreaking techniques on the AdvBench subset dataset, achieving 29-61% higher performance on GPT-4 and 49-71% on Gemini-Pro. Finally, we also demonstrate Crescendo's ability to jailbreak multimodal models.

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safeguards, leading LLMs to generate potentially harmful content. Exploring jailbreak prompts can help to better reveal the weaknesses of LLMs and further steer us to secure them. Unfortunately, existing jailbreak methods either suffer from intricate manual design or require optimization on other white-box models, which compromises either generalization or efficiency. In this paper, we generalize jailbreak prompt attacks into two aspects: (1) Prompt Rewriting and (2) Scenario Nesting. Based on this, we propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts. Extensive experiments demonstrate that ReNeLLM significantly improves the attack success rate while greatly reducing the time cost compared to existing baselines. Our study also reveals the inadequacy of current defense methods in safeguarding LLMs. Finally, we analyze the failure of LLMs defense from the perspective of prompt execution priority, and propose corresponding defense strategies. We hope that our research can catalyze both the academic community and LLMs developers towards the provision of safer and more regulated LLMs. The code is available at https://github.com/NJUNLP/ReNeLLM.

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails. Universal jailbreaks - prefixes that can circumvent alignment for any payload - are particularly concerning. We show empirically that jailbreak detection systems face distribution shift, with detectors trained at one point in time performing poorly against newer exploits. To study this problem, we release JailbreaksOverTime, a comprehensive dataset of timestamped real user interactions containing both benign requests and jailbreak attempts collected over 10 months. We propose a two-pronged method for defenders to detect new jailbreaks and continuously update their detectors. First, we show how to use continuous learning to detect jailbreaks and adapt rapidly to new emerging jailbreaks. While detectors trained at a single point in time eventually fail due to drift, we find that universal jailbreaks evolve slowly enough for self-training to be effective. Retraining our detection model weekly using its own labels - with no new human labels - reduces the false negative rate from 4% to 0.3% at a false positive rate of 0.1%. Second, we introduce an unsupervised active monitoring approach to identify novel jailbreaks. Rather than classifying inputs directly, we recognize jailbreaks by their behavior, specifically, their ability to trigger models to respond to known-harmful prompts. This approach has a higher false negative rate (4.1%) than supervised methods, but it successfully identified some out-of-distribution attacks that were missed by the continuous learning approach.

Along with the remarkable successes of Language language models, recent research also started to explore the security threats of LLMs, including jailbreaking attacks. Attackers carefully craft jailbreaking prompts such that a target LLM will respond to the harmful question. Existing jailbreaking attacks require either human experts or leveraging complicated algorithms to craft jailbreaking prompts. In this paper, we introduce BOOST, a simple attack that leverages only the eos tokens. We demonstrate that rather than constructing complicated jailbreaking prompts, the attacker can simply append a few eos tokens to the end of a harmful question. It will bypass the safety alignment of LLMs and lead to successful jailbreaking attacks. We further apply BOOST to four representative jailbreak methods and show that the attack success rates of these methods can be significantly enhanced by simply adding eos tokens to the prompt. To understand this simple but novel phenomenon, we conduct empirical analyses. Our analysis reveals that adding eos tokens makes the target LLM believe the input is much less harmful, and eos tokens have low attention values and do not affect LLM's understanding of the harmful questions, leading the model to actually respond to the questions. Our findings uncover how fragile an LLM is against jailbreak attacks, motivating the development of strong safety alignment approaches.

Ensuring AI safety is crucial as large language models become increasingly integrated into real-world applications. A key challenge is jailbreak, where adversarial prompts bypass built-in safeguards to elicit harmful disallowed outputs. Inspired by psychological foot-in-the-door principles, we introduce FITD,a novel multi-turn jailbreak method that leverages the phenomenon where minor initial commitments lower resistance to more significant or more unethical transgressions. Our approach progressively escalates the malicious intent of user queries through intermediate bridge prompts and aligns the model's response by itself to induce toxic responses. Extensive experimental results on two jailbreak benchmarks demonstrate that FITD achieves an average attack success rate of 94% across seven widely used models, outperforming existing state-of-the-art methods. Additionally, we provide an in-depth analysis of LLM self-corruption, highlighting vulnerabilities in current alignment strategies and emphasizing the risks inherent in multi-turn interactions. The code is available at https://github.com/Jinxiaolong1129/Foot-in-the-door-Jailbreak.

Large Language Models (LLMs), like ChatGPT, have demonstrated vast potential but also introduce challenges related to content constraints and potential misuse. Our study investigates three key research questions: (1) the number of different prompt types that can jailbreak LLMs, (2) the effectiveness of jailbreak prompts in circumventing LLM constraints, and (3) the resilience of ChatGPT against these jailbreak prompts. Initially, we develop a classification model to analyze the distribution of existing prompts, identifying ten distinct patterns and three categories of jailbreak prompts. Subsequently, we assess the jailbreak capability of prompts with ChatGPT versions 3.5 and 4.0, utilizing a dataset of 3,120 jailbreak questions across eight prohibited scenarios. Finally, we evaluate the resistance of ChatGPT against jailbreak prompts, finding that the prompts can consistently evade the restrictions in 40 use-case scenarios. The study underscores the importance of prompt structures in jailbreaking LLMs and discusses the challenges of robust jailbreak prompt generation and prevention.

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass safety mechanisms in models, leading to the generation of inappropriate or unsafe content. Detecting such attacks is critical to ensuring the responsible deployment of MLLMs. Existing jailbreak detection methods face three primary challenges: (1) Many rely on model hidden states or gradients, limiting their applicability to white-box models, where the internal workings of the model are accessible; (2) They involve high computational overhead from uncertainty-based analysis, which limits real-time detection, and (3) They require fully labeled harmful datasets, which are often scarce in real-world settings. To address these issues, we introduce a test-time adaptive framework called JAILDAM. Our method leverages a memory-based approach guided by policy-driven unsafe knowledge representations, eliminating the need for explicit exposure to harmful data. By dynamically updating unsafe knowledge during test-time, our framework improves generalization to unseen jailbreak strategies while maintaining efficiency. Experiments on multiple VLM jailbreak benchmarks demonstrate that JAILDAM delivers state-of-the-art performance in harmful content detection, improving both accuracy and speed.

Despite prior safety alignment efforts, mainstream LLMs can still generate harmful and unethical content when subjected to jailbreaking attacks. Existing jailbreaking methods fall into two main categories: template-based and optimization-based methods. The former requires significant manual effort and domain knowledge, while the latter, exemplified by Greedy Coordinate Gradient (GCG), which seeks to maximize the likelihood of harmful LLM outputs through token-level optimization, also encounters several limitations: requiring white-box access, necessitating pre-constructed affirmative phrase, and suffering from low efficiency. In this paper, we present ECLIPSE, a novel and efficient black-box jailbreaking method utilizing optimizable suffixes. Drawing inspiration from LLMs' powerful generation and optimization capabilities, we employ task prompts to translate jailbreaking goals into natural language instructions. This guides the LLM to generate adversarial suffixes for malicious queries. In particular, a harmfulness scorer provides continuous feedback, enabling LLM self-reflection and iterative optimization to autonomously and efficiently produce effective suffixes. Experimental results demonstrate that ECLIPSE achieves an average attack success rate (ASR) of 0.92 across three open-source LLMs and GPT-3.5-Turbo, significantly surpassing GCG in 2.4 times. Moreover, ECLIPSE is on par with template-based methods in ASR while offering superior attack efficiency, reducing the average attack overhead by 83%.

We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics, and then composes multiple tactics for systematic exploration of novel jailbreaks. Compared to prior work that performed red-teaming via recruited human workers, gradient-based optimization, or iterative revision with LLMs, our work investigates jailbreaks from chatbot users who were not specifically instructed to break the system. WildTeaming reveals previously unidentified vulnerabilities of frontier LLMs, resulting in up to 4.6x more diverse and successful adversarial attacks compared to state-of-the-art jailbreak methods. While many datasets exist for jailbreak evaluation, very few open-source datasets exist for jailbreak training, as safety training data has been closed even when model weights are open. With WildTeaming we create WildJailbreak, a large-scale open-source synthetic safety dataset with 262K vanilla (direct request) and adversarial (complex jailbreak) prompt-response pairs. To mitigate exaggerated safety behaviors, WildJailbreak provides two contrastive types of queries: 1) harmful queries (vanilla & adversarial) and 2) benign queries that resemble harmful queries in form but contain no harm. As WildJailbreak considerably upgrades the quality and scale of existing safety resources, it uniquely enables us to examine the scaling effects of data and the interplay of data properties and model capabilities during safety training. Through extensive experiments, we identify the training properties that enable an ideal balance of safety behaviors: appropriate safeguarding without over-refusal, effective handling of vanilla and adversarial queries, and minimal, if any, decrease in general capabilities. All components of WildJailbeak contribute to achieving balanced safety behaviors of models.

This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A maximum likelihood-based algorithm is proposed to find an image Jailbreaking Prompt (imgJP), enabling jailbreaks against MLLMs across multiple unseen prompts and images (i.e., data-universal property). Our approach exhibits strong model-transferability, as the generated imgJP can be transferred to jailbreak various models, including MiniGPT-v2, LLaVA, InstructBLIP, and mPLUG-Owl2, in a black-box manner. Moreover, we reveal a connection between MLLM-jailbreaks and LLM-jailbreaks. As a result, we introduce a construction-based method to harness our approach for LLM-jailbreaks, demonstrating greater efficiency than current state-of-the-art methods. The code is available here. Warning: some content generated by language models may be offensive to some readers.

Many-shot jailbreaking circumvents the safety alignment of large language models by exploiting their ability to process long input sequences. To achieve this, the malicious target prompt is prefixed with hundreds of fabricated conversational turns between the user and the model. These fabricated exchanges are randomly sampled from a pool of malicious questions and responses, making it appear as though the model has already complied with harmful instructions. In this paper, we present PANDAS: a hybrid technique that improves many-shot jailbreaking by modifying these fabricated dialogues with positive affirmations, negative demonstrations, and an optimized adaptive sampling method tailored to the target prompt's topic. Extensive experiments on AdvBench and HarmBench, using state-of-the-art LLMs, demonstrate that PANDAS significantly outperforms baseline methods in long-context scenarios. Through an attention analysis, we provide insights on how long-context vulnerabilities are exploited and show how PANDAS further improves upon many-shot jailbreaking.

Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a novel type of jailbreak, which triggers T2I models to generate the image with visual text, where the image and the text, although considered to be safe in isolation, combine to form unsafe content. To systematically explore this phenomenon, we propose a dataset to evaluate the current diffusion-based text-to-image (T2I) models under such jailbreak. We benchmark nine representative T2I models, including two close-source commercial models. Experimental results reveal a concerning tendency to produce unsafe content: all tested models suffer from such type of jailbreak, with rates of unsafe generation ranging from 8\% to 74\%. In real-world scenarios, various filters such as keyword blocklists, customized prompt filters, and NSFW image filters, are commonly employed to mitigate these risks. We evaluate the effectiveness of such filters against our jailbreak and found that, while current classifiers may be effective for single modality detection, they fail to work against our jailbreak. Our work provides a foundation for further development towards more secure and reliable T2I models.

Recent large language model (LLM) defenses have greatly improved models' ability to refuse harmful queries, even when adversarially attacked. However, LLM defenses are primarily evaluated against automated adversarial attacks in a single turn of conversation, an insufficient threat model for real-world malicious use. We demonstrate that multi-turn human jailbreaks uncover significant vulnerabilities, exceeding 70% attack success rate (ASR) on HarmBench against defenses that report single-digit ASRs with automated single-turn attacks. Human jailbreaks also reveal vulnerabilities in machine unlearning defenses, successfully recovering dual-use biosecurity knowledge from unlearned models. We compile these results into Multi-Turn Human Jailbreaks (MHJ), a dataset of 2,912 prompts across 537 multi-turn jailbreaks. We publicly release MHJ alongside a compendium of jailbreak tactics developed across dozens of commercial red teaming engagements, supporting research towards stronger LLM defenses.

Large language models (LLMs) have achieved significant advances in recent days. Extensive efforts have been made before the public release of LLMs to align their behaviors with human values. The primary goal of alignment is to ensure their helpfulness, honesty and harmlessness. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as jailbreaking, leading to unintended behaviors. The jailbreak is to intentionally develop a malicious prompt that escapes from the LLM security restrictions to produce uncensored detrimental contents. Previous works explore different jailbreak methods for red teaming LLMs, yet they encounter challenges regarding to effectiveness and scalability. In this work, we propose Tastle, a novel black-box jailbreak framework for automated red teaming of LLMs. We designed malicious content concealing and memory reframing with an iterative optimization algorithm to jailbreak LLMs, motivated by the research about the distractibility and over-confidence phenomenon of LLMs. Extensive experiments of jailbreaking both open-source and proprietary LLMs demonstrate the superiority of our framework in terms of effectiveness, scalability and transferability. We also evaluate the effectiveness of existing jailbreak defense methods against our attack and highlight the crucial need to develop more effective and practical defense strategies.

In recent years, the rapid development of large language models (LLMs) has brought new vitality to the various domains and generated substantial social and economic benefits. However, the swift advancement of LLMs has introduced new security vulnerabilities. Jailbreak, a form of attack that induces LLMs to output harmful content through carefully crafted prompts, poses a challenge to the safe and trustworthy development of LLMs. Previous jailbreak attack methods primarily exploited the internal capabilities of the model. Among them, one category leverages the model's implicit capabilities for jailbreak attacks, where the attacker is unaware of the exact reasons for the attack's success. The other category utilizes the model's explicit capabilities for jailbreak attacks, where the attacker understands the reasons for the attack's success. For example, these attacks exploit the model's abilities in coding, contextual learning, or understanding ASCII characters. However, these earlier jailbreak attacks have certain limitations, as they only exploit the inherent capabilities of the model. In this paper, we propose a novel jailbreak method, SQL Injection Jailbreak (SIJ), which utilizes the construction of input prompts by LLMs to inject jailbreak information into user prompts, enabling successful jailbreak of the LLMs. Our SIJ method achieves nearly 100\% attack success rates on five well-known open-source LLMs in the context of AdvBench, while incurring lower time costs compared to previous methods. More importantly, SIJ reveals a new vulnerability in LLMs that urgently needs to be addressed. To this end, we propose a defense method called Self-Reminder-Key and demonstrate its effectiveness through experiments. Our code is available at https://github.com/weiyezhimeng/SQL-Injection-Jailbreak{https://github.com/weiyezhimeng/SQL-Injection-Jailbreak}.

There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, which coax LLMs into overriding their safety guardrails. The identification of these vulnerabilities is therefore instrumental in understanding inherent weaknesses and preventing future misuse. To this end, we propose Prompt Automatic Iterative Refinement (PAIR), an algorithm that generates semantic jailbreaks with only black-box access to an LLM. PAIR -- which is inspired by social engineering attacks -- uses an attacker LLM to automatically generate jailbreaks for a separate targeted LLM without human intervention. In this way, the attacker LLM iteratively queries the target LLM to update and refine a candidate jailbreak. Empirically, PAIR often requires fewer than twenty queries to produce a jailbreak, which is orders of magnitude more efficient than existing algorithms. PAIR also achieves competitive jailbreaking success rates and transferability on open and closed-source LLMs, including GPT-3.5/4, Vicuna, and PaLM-2.

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks mainly rely on scenario camouflage, prompt obfuscation, prompt optimization, and prompt iterative optimization to conceal malicious prompts. In particular, sequential prompt chains in a single query can lead LLMs to focus on certain prompts while ignoring others, facilitating context manipulation. This paper introduces SequentialBreak, a novel jailbreak attack that exploits this vulnerability. We discuss several scenarios, not limited to examples like Question Bank, Dialog Completion, and Game Environment, where the harmful prompt is embedded within benign ones that can fool LLMs into generating harmful responses. The distinct narrative structures of these scenarios show that SequentialBreak is flexible enough to adapt to various prompt formats beyond those discussed. Extensive experiments demonstrate that SequentialBreak uses only a single query to achieve a substantial gain of attack success rate over existing baselines against both open-source and closed-source models. Through our research, we highlight the urgent need for more robust and resilient safeguards to enhance LLM security and prevent potential misuse. All the result files and website associated with this research are available in this GitHub repository: https://anonymous.4open.science/r/JailBreakAttack-4F3B/.

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with minimal effort. This dual high performance in both attack and defense raises a fundamental and perplexing paradox. To gain a deep understanding of this issue and thus further help strengthen the trustworthiness of VLLMs, this paper makes three key contributions: i) One tentative explanation for VLLMs being prone to jailbreak attacks--inclusion of vision inputs, as well as its in-depth analysis. ii) The recognition of a largely ignored problem in existing defense mechanisms--over-prudence. The problem causes these defense methods to exhibit unintended abstention, even in the presence of benign inputs, thereby undermining their reliability in faithfully defending against attacks. iii) A simple safety-aware method--LLM-Pipeline. Our method repurposes the more advanced guardrails of LLMs on the shelf, serving as an effective alternative detector prior to VLLM response. Last but not least, we find that the two representative evaluation methods for jailbreak often exhibit chance agreement. This limitation makes it potentially misleading when evaluating attack strategies or defense mechanisms. We believe the findings from this paper offer useful insights to rethink the foundational development of VLLM safety with respect to benchmark datasets, defense strategies, and evaluation methods.

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a novel benchmark construction framework that "distills" jailbreak attacks into high-quality and easily-updatable safety benchmarks. JBDistill utilizes a small set of development models and existing jailbreak attack algorithms to create a candidate prompt pool, then employs prompt selection algorithms to identify an effective subset of prompts as safety benchmarks. JBDistill addresses challenges in existing safety evaluation: the use of consistent evaluation prompts across models ensures fair comparisons and reproducibility. It requires minimal human effort to rerun the JBDistill pipeline and produce updated benchmarks, alleviating concerns on saturation and contamination. Extensive experiments demonstrate our benchmarks generalize robustly to 13 diverse evaluation models held out from benchmark construction, including proprietary, specialized, and newer-generation LLMs, significantly outperforming existing safety benchmarks in effectiveness while maintaining high separability and diversity. Our framework thus provides an effective, sustainable, and adaptable solution for streamlining safety evaluation.

Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use agents. Yet, the safety implications of these extended contexts remain unclear. To bridge this gap, we introduce NINJA (short for Needle-in-haystack jailbreak attack), a method that jailbreaks aligned LMs by appending benign, model-generated content to harmful user goals. Critical to our method is the observation that the position of harmful goals play an important role in safety. Experiments on standard safety benchmark, HarmBench, show that NINJA significantly increases attack success rates across state-of-the-art open and proprietary models, including LLaMA, Qwen, Mistral, and Gemini. Unlike prior jailbreaking methods, our approach is low-resource, transferable, and less detectable. Moreover, we show that NINJA is compute-optimal -- under a fixed compute budget, increasing context length can outperform increasing the number of trials in best-of-N jailbreak. These findings reveal that even benign long contexts -- when crafted with careful goal positioning -- introduce fundamental vulnerabilities in modern LMs.

In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), and use them for red-teaming. As a result, AutoDAN-Turbo can significantly outperform baseline methods, achieving a 74.3% higher average attack success rate on public benchmarks. Notably, AutoDAN-Turbo achieves an 88.5 attack success rate on GPT-4-1106-turbo. In addition, AutoDAN-Turbo is a unified framework that can incorporate existing human-designed jailbreak strategies in a plug-and-play manner. By integrating human-designed strategies, AutoDAN-Turbo can even achieve a higher attack success rate of 93.4 on GPT-4-1106-turbo.

Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to image-based jailbreaks crafted to induce harmful responses. Existing gradient-based jailbreak methods transfer poorly, as adversarial patterns overfit to a single white-box surrogate and fail to generalise to black-box models. In this work, we propose Universal and transferable jailbreak (UltraBreak), a framework that constrains adversarial patterns through transformations and regularisation in the vision space, while relaxing textual targets through semantic-based objectives. By defining its loss in the textual embedding space of the target LLM, UltraBreak discovers universal adversarial patterns that generalise across diverse jailbreak objectives. This combination of vision-level regularisation and semantically guided textual supervision mitigates surrogate overfitting and enables strong transferability across both models and attack targets. Extensive experiments show that UltraBreak consistently outperforms prior jailbreak methods. Further analysis reveals why earlier approaches fail to transfer, highlighting that smoothing the loss landscape via semantic objectives is crucial for enabling universal and transferable jailbreaks. The code is publicly available in our https://github.com/kaiyuanCui/UltraBreak{GitHub repository}.

Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, alongside their impressive capabilities, ethical concerns and new types of attacks, such as jailbreaking, have emerged. While most prompting techniques focus on optimizing adversarial inputs for individual cases, resulting in higher computational costs when dealing with large datasets. Less research has addressed the more general setting of training a universal attacker that can transfer to unseen tasks. In this paper, we introduce JUMP, a prompt-based method designed to jailbreak LLMs using universal multi-prompts. We also adapt our approach for defense, which we term DUMP. Experimental results demonstrate that our method for optimizing universal multi-prompts outperforms existing techniques.

We introduce self-jailbreaking, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no external red-team LLM: the target model's own internal knowledge suffices. We operationalize this via Self-Jailbreaking via Lexical Insertion Prompting (\textsc{SLIP)}, a black-box algorithm that casts jailbreaking as breadth-first tree search over multi-turn dialogues, incrementally inserting missing content words from the attack goal into benign prompts using the target model as its own guide. Evaluations on AdvBench and HarmBench show SLIP achieves 90--100\% Attack Success Rate (ASR) (avg.\ 94.7\%) across most of the eleven tested models (including GPT-5.1, Claude-Sonnet-4.5, Gemini-2.5-Pro, and DeepSeek-V3), with only {sim}7.9 LLM calls on average, 3--6times fewer than prior methods. We evaluate existing defenses, show that regex-based approaches are evaded by prompt paraphrasing, and propose the Semantic Drift Monitor (SDM) defense that tracks SLIP's embedding-space trajectory, achieving 76\% detection at 5\% FPR. However, SDM remains insufficient against adaptive attack strategies, underscoring the need for more advanced defense mechanisms tailored to the self-jailbreaking threat surface. We release our code for reproducibility.

A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can jailbreak an MLLM and cause unaligned behaviors. In this work, we report an even more severe safety issue in multi-agent environments, referred to as infectious jailbreak. It entails the adversary simply jailbreaking a single agent, and without any further intervention from the adversary, (almost) all agents will become infected exponentially fast and exhibit harmful behaviors. To validate the feasibility of infectious jailbreak, we simulate multi-agent environments containing up to one million LLaVA-1.5 agents, and employ randomized pair-wise chat as a proof-of-concept instantiation for multi-agent interaction. Our results show that feeding an (infectious) adversarial image into the memory of any randomly chosen agent is sufficient to achieve infectious jailbreak. Finally, we derive a simple principle for determining whether a defense mechanism can provably restrain the spread of infectious jailbreak, but how to design a practical defense that meets this principle remains an open question to investigate. Our project page is available at https://sail-sg.github.io/Agent-Smith/.

Refusal training on Large Language Models (LLMs) prevents harmful outputs, yet this defense remains vulnerable to both automated and human-crafted jailbreaks. We present a novel LLM-as-red-teamer approach in which a human jailbreaks a refusal-trained LLM to make it willing to jailbreak itself or other LLMs. We refer to the jailbroken LLMs as J_2 attackers, which can systematically evaluate target models using various red teaming strategies and improve its performance via in-context learning from the previous failures. Our experiments demonstrate that Sonnet 3.5 and Gemini 1.5 pro outperform other LLMs as J_2, achieving 93.0% and 91.0% attack success rates (ASRs) respectively against GPT-4o (and similar results across other capable LLMs) on Harmbench. Our work not only introduces a scalable approach to strategic red teaming, drawing inspiration from human red teamers, but also highlights jailbreaking-to-jailbreak as an overlooked failure mode of the safeguard. Specifically, an LLM can bypass its own safeguards by employing a jailbroken version of itself that is willing to assist in further jailbreaking. To prevent any direct misuse with J_2, while advancing research in AI safety, we publicly share our methodology while keeping specific prompting details private.

Various jailbreak attacks have been proposed to red-team Large Language Models (LLMs) and revealed the vulnerable safeguards of LLMs. Besides, some methods are not limited to the textual modality and extend the jailbreak attack to Multimodal Large Language Models (MLLMs) by perturbing the visual input. However, the absence of a universal evaluation benchmark complicates the performance reproduction and fair comparison. Besides, there is a lack of comprehensive evaluation of closed-source state-of-the-art (SOTA) models, especially MLLMs, such as GPT-4V. To address these issues, this work first builds a comprehensive jailbreak evaluation dataset with 1445 harmful questions covering 11 different safety policies. Based on this dataset, extensive red-teaming experiments are conducted on 11 different LLMs and MLLMs, including both SOTA proprietary models and open-source models. We then conduct a deep analysis of the evaluated results and find that (1) GPT4 and GPT-4V demonstrate better robustness against jailbreak attacks compared to open-source LLMs and MLLMs. (2) Llama2 and Qwen-VL-Chat are more robust compared to other open-source models. (3) The transferability of visual jailbreak methods is relatively limited compared to textual jailbreak methods. The dataset and code can be found here https://anonymous.4open.science/r/red_teaming_gpt4-C1CE/README.md .

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specific harmful parameters, current methods remain vulnerable to diverse jailbreaks. We first conduct an empirical study and discover that this failure mechanism is caused by jailbreaks primarily activating non-erased parameters in the intermediate layers. Further, by probing the underlying mechanism through which these circumvented parameters reassemble into the prohibited output, we verify the persistent existence of dynamic jailbreak paths and show that the inability to rectify them constitutes the fundamental gap in existing unlearning defenses. To bridge this gap, we propose Jailbreak Path Unlearning (JPU), which is the first to rectify dynamic jailbreak paths towards safety anchors by dynamically mining on-policy adversarial samples to expose vulnerabilities and identify jailbreak paths. Extensive experiments demonstrate that JPU significantly enhances jailbreak resistance against dynamic attacks while preserving the model's utility.

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this balance. Existing defenses, such as prompt engineering and safety fine-tuning, often introduce computational overhead, increase inference latency, and lack runtime flexibility. Moreover, overly restrictive safety measures can degrade model utility by causing refusals of benign queries. In this paper, we introduce Jailbreak Antidote, a method that enables real-time adjustment of LLM safety preferences by manipulating a sparse subset of the model's internal states during inference. By shifting the model's hidden representations along a safety direction with varying strengths, we achieve flexible control over the safety-utility balance without additional token overhead or inference delays. Our analysis reveals that safety-related information in LLMs is sparsely distributed; adjusting approximately 5% of the internal state is as effective as modifying the entire state. Extensive experiments on nine LLMs (ranging from 2 billion to 72 billion parameters), evaluated against ten jailbreak attack methods and compared with six defense strategies, validate the effectiveness and efficiency of our approach. By directly manipulating internal states during reasoning, Jailbreak Antidote offers a lightweight, scalable solution that enhances LLM safety while preserving utility, opening new possibilities for real-time safety mechanisms in widely-deployed AI systems.

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic suffixes). In this paper, we introduce imperceptible jailbreaks that exploit a class of Unicode characters called variation selectors. By appending invisible variation selectors to malicious questions, the jailbreak prompts appear visually identical to original malicious questions on screen, while their tokenization is "secretly" altered. We propose a chain-of-search pipeline to generate such adversarial suffixes to induce harmful responses. Our experiments show that our imperceptible jailbreaks achieve high attack success rates against four aligned LLMs and generalize to prompt injection attacks, all without producing any visible modifications in the written prompt. Our code is available at https://github.com/sail-sg/imperceptible-jailbreaks.

The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing red-teaming frameworks focus on single-turn attacks, real-world adversaries typically operate in multi-turn scenarios, iteratively probing for vulnerabilities and adapting their prompts based on threat model responses. In this paper, we propose \AlgName, a novel multi-turn red-teaming agent that emulates sophisticated human attackers through complementary learning dimensions: global tactic-wise learning that accumulates knowledge over time and generalizes to new attack goals, and local prompt-wise learning that refines implementations for specific goals when initial attempts fail. Unlike previous multi-turn approaches that rely on fixed strategy sets, \AlgName enables the agent to identify new jailbreak tactics, develop a goal-based tactic selection framework, and refine prompt formulations for selected tactics. Empirical evaluations on JailbreakBench demonstrate our framework's superior performance, achieving over 90\% attack success rates against GPT-3.5-Turbo and Llama-3.1-70B within 5 conversation turns, outperforming state-of-the-art baselines. These results highlight the effectiveness of dynamic learning in identifying and exploiting model vulnerabilities in realistic multi-turn scenarios.

Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more autonomously in higher-stakes settings may similarly be vulnerable to such attacks. Prior work has studied jailbreak success by examining the model's intermediate representations, identifying directions in this space that causally encode concepts like harmfulness and refusal. Then, they globally explain all jailbreak attacks as attempting to reduce or strengthen these concepts (e.g., reduce harmfulness). However, different jailbreak strategies may succeed by strengthening or suppressing different intermediate concepts, and the same jailbreak strategy may not work for different harmful request categories (e.g., violence vs. cyberattack); thus, we seek to give a local explanation -- i.e., why did this specific jailbreak succeed? To address this gap, we introduce LOCA, a method that gives Local, CAusal explanations of jailbreak success by identifying a minimal set of interpretable, intermediate representation changes that causally induce model refusal on an otherwise successful jailbreak request. We evaluate LOCA on harmful original-jailbreak pairs from a large jailbreak benchmark across Gemma and Llama chat models, comparing against prior methods adapted to this setting. LOCA can successfully induce refusal by making, on average, six interpretable changes; prior work routinely fails to achieve refusal even after 20 changes. LOCA is a step toward mechanistic, local explanations of jailbreak success in LLMs. Code to be released.

While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with Pruning (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM. TAP utilizes an LLM to iteratively refine candidate (attack) prompts using tree-of-thoughts reasoning until one of the generated prompts jailbreaks the target. Crucially, before sending prompts to the target, TAP assesses them and prunes the ones unlikely to result in jailbreaks. Using tree-of-thought reasoning allows TAP to navigate a large search space of prompts and pruning reduces the total number of queries sent to the target. In empirical evaluations, we observe that TAP generates prompts that jailbreak state-of-the-art LLMs (including GPT4 and GPT4-Turbo) for more than 80% of the prompts using only a small number of queries. This significantly improves upon the previous state-of-the-art black-box method for generating jailbreaks.

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into producing harmful outputs. Existing jailbreaks are either black-box, using carefully crafted, unstealthy prompts, or white-box, requiring resource-intensive computation. In light of these challenges, we introduce ShallowJail, a novel attack that exploits shallow alignment in LLMs. ShallowJail can misguide LLMs' responses by manipulating the initial tokens during inference. Through extensive experiments, we demonstrate the effectiveness of~\shallow, which substantially degrades the safety of state-of-the-art LLM responses.

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with jailbreaks prior to the release. Therefore, such testing will require a method that can generate jailbreaks massively and efficiently. In this paper, we follow a novel yet intuitive strategy to generate jailbreaks in the style of the human generation. We propose a role-playing system that assigns four different roles to the user LLMs to collaborate on new jailbreaks. Furthermore, we collect existing jailbreaks and split them into different independent characteristics using clustering frequency and semantic patterns sentence by sentence. We organize these characteristics into a knowledge graph, making them more accessible and easier to retrieve. Our system of different roles will leverage this knowledge graph to generate new jailbreaks, which have proved effective in inducing LLMs to generate unethical or guideline-violating responses. In addition, we also pioneer a setting in our system that will automatically follow the government-issued guidelines to generate jailbreaks to test whether LLMs follow the guidelines accordingly. We refer to our system as GUARD (Guideline Upholding through Adaptive Role-play Diagnostics). We have empirically validated the effectiveness of GUARD on three cutting-edge open-sourced LLMs (Vicuna-13B, LongChat-7B, and Llama-2-7B), as well as a widely-utilized commercial LLM (ChatGPT). Moreover, our work extends to the realm of vision language models (MiniGPT-v2 and Gemini Vision Pro), showcasing GUARD's versatility and contributing valuable insights for the development of safer, more reliable LLM-based applications across diverse modalities.

Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM defenses remains a challenge, with current methods often lacking explainability and generalization to complex scenarios, leading to incomplete assessments (e.g., direct judgment without reasoning, low F1 score of GPT-4 in complex cases, bias in multilingual scenarios). To address this, we present JAILJUDGE, a comprehensive benchmark featuring diverse risk scenarios, including synthetic, adversarial, in-the-wild, and multilingual prompts, along with high-quality human-annotated datasets. The JAILJUDGE dataset includes over 35k+ instruction-tune data with reasoning explainability and JAILJUDGETEST, a 4.5k+ labeled set for risk scenarios, and a 6k+ multilingual set across ten languages. To enhance evaluation with explicit reasoning, we propose the JailJudge MultiAgent framework, which enables explainable, fine-grained scoring (1 to 10). This framework supports the construction of instruction-tuning ground truth and facilitates the development of JAILJUDGE Guard, an end-to-end judge model that provides reasoning and eliminates API costs. Additionally, we introduce JailBoost, an attacker-agnostic attack enhancer, and GuardShield, a moderation defense, both leveraging JAILJUDGE Guard. Our experiments demonstrate the state-of-the-art performance of JailJudge methods (JailJudge MultiAgent, JAILJUDGE Guard) across diverse models (e.g., GPT-4, Llama-Guard) and zero-shot scenarios. JailBoost and GuardShield significantly improve jailbreak attack and defense tasks under zero-shot settings, with JailBoost enhancing performance by 29.24% and GuardShield reducing defense ASR from 40.46% to 0.15%.

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with additional safety properties to defend against these attacks. However, tuning large models has become increasingly resource intensive and may have difficulty ensuring consistent performance. We introduce Speculative Safety-Aware Decoding (SSD), a lightweight decoding-time approach that equips LLMs with the desired safety property while accelerating inference. We assume that there exists a small language model that possesses this desired property. SSD integrates speculative sampling during decoding and leverages the match ratio between the small and composite models to quantify jailbreak risks. This enables SSD to dynamically switch between decoding schemes to prioritize utility or safety, to handle the challenge of different model capacities. The output token is then sampled from a new distribution that combines the distributions of the original and the small models. Experimental results show that SSD successfully equips the large model with the desired safety property, and also allows the model to remain helpful to benign queries. Furthermore, SSD accelerates the inference time, thanks to the speculative sampling design.

Large Language Models (LLMs) are commonly evaluated for robustness against paraphrased or semantically equivalent jailbreak prompts, yet little attention has been paid to linguistic variation as an attack surface. In this work, we systematically study how linguistic styles such as fear or curiosity can reframe harmful intent and elicit unsafe responses from aligned models. We construct style-augmented jailbreak benchmark by transforming prompts from 3 standard datasets into 11 distinct linguistic styles using handcrafted templates and LLM-based rewrites, while preserving semantic intent. Evaluating 16 open- and close-source instruction-tuned models, we find that stylistic reframing increases jailbreak success rates by up to +57 percentage points. Styles such as fearful, curious and compassionate are most effective and contextualized rewrites outperform templated variants. To mitigate this, we introduce a style neutralization preprocessing step using a secondary LLM to strip manipulative stylistic cues from user inputs, significantly reducing jailbreak success rates. Our findings reveal a systemic and scaling-resistant vulnerability overlooked in current safety pipelines.

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire harmful prompts, are not effective at concealing malicious intent and can be easily identified and rejected by well-aligned LLMs. This paper discovers that decomposing a malicious prompt into separated sub-prompts can effectively obscure its underlying malicious intent by presenting it in a fragmented, less detectable form, thereby addressing these limitations. We introduce an automatic prompt Decomposition and Reconstruction framework for jailbreak Attack (DrAttack). DrAttack includes three key components: (a) `Decomposition' of the original prompt into sub-prompts, (b) `Reconstruction' of these sub-prompts implicitly by in-context learning with semantically similar but harmless reassembling demo, and (c) a `Synonym Search' of sub-prompts, aiming to find sub-prompts' synonyms that maintain the original intent while jailbreaking LLMs. An extensive empirical study across multiple open-source and closed-source LLMs demonstrates that, with a significantly reduced number of queries, DrAttack obtains a substantial gain of success rate over prior SOTA prompt-only attackers. Notably, the success rate of 78.0\% on GPT-4 with merely 15 queries surpassed previous art by 33.1\%. The project is available at https://github.com/xirui-li/DrAttack.

Large Language Models (LLMs) continue to advance in their capabilities, yet this progress is accompanied by a growing array of safety risks. While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of exploration into defending against these attacks. We point out a pivotal factor contributing to the success of jailbreaks: the inherent conflict between the goals of being helpful and ensuring safety. To counter jailbreaking attacks, we propose to integrate goal prioritization at both training and inference stages. Implementing goal prioritization during inference substantially diminishes the Attack Success Rate (ASR) of jailbreaking attacks, reducing it from 66.4% to 2.0% for ChatGPT and from 68.2% to 19.4% for Vicuna-33B, without compromising general performance. Furthermore, integrating the concept of goal prioritization into the training phase reduces the ASR from 71.0% to 6.6% for LLama2-13B. Remarkably, even in scenarios where no jailbreaking samples are included during training, our approach slashes the ASR by half, decreasing it from 71.0% to 34.0%. Additionally, our findings reveal that while stronger LLMs face greater safety risks, they also possess a greater capacity to be steered towards defending against such attacks. We hope our work could contribute to the comprehension of jailbreaking attacks and defenses, and shed light on the relationship between LLMs' capability and safety. Our code will be available at https://github.com/thu-coai/JailbreakDefense_GoalPriority.

With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while align- ing them with human values has emerged as a critical challenge. In this paper, we investigate an important and unexplored question of whether techniques that successfully jailbreak Large Language Models (LLMs) can be equally effective in jailbreaking MLLMs. To explore this issue, we in- troduce JailBreakV-28K, a pioneering benchmark designed to assess the transferability of LLM jailbreak techniques to MLLMs, thereby evaluat- ing the robustness of MLLMs against diverse jailbreak attacks. Utilizing a dataset of 2, 000 malicious queries that is also proposed in this paper, we generate 20, 000 text-based jailbreak prompts using advanced jailbreak attacks on LLMs, alongside 8, 000 image-based jailbreak inputs from recent MLLMs jailbreak attacks, our comprehensive dataset includes 28, 000 test cases across a spectrum of adversarial scenarios. Our evaluation of 10 open- source MLLMs reveals a notably high Attack Success Rate (ASR) for attacks transferred from LLMs, highlighting a critical vulnerability in MLLMs that stems from their text-processing capabilities. Our findings underscore the urgent need for future research to address alignment vulnerabilities in MLLMs from both textual and visual inputs.

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term involuntary jailbreak. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific attack objective, such as generating instructions for building a bomb. Prior attack methods predominantly target localized components of the LLM guardrail. In contrast, involuntary jailbreaks may potentially compromise the entire guardrail structure, which our method reveals to be surprisingly fragile. We merely employ a single universal prompt to achieve this goal. In particular, we instruct LLMs to generate several questions that would typically be rejected, along with their corresponding in-depth responses (rather than a refusal). Remarkably, this simple prompt strategy consistently jailbreaks the majority of leading LLMs, including Claude Opus 4.1, Grok 4, Gemini 2.5 Pro, and GPT 4.1. We hope this problem can motivate researchers and practitioners to re-evaluate the robustness of LLM guardrails and contribute to stronger safety alignment in future.

The rapid progress in open-source large language models (LLMs) is significantly advancing AI development. Extensive efforts have been made before model release to align their behavior with human values, with the primary goal of ensuring their helpfulness and harmlessness. However, even carefully aligned models can be manipulated maliciously, leading to unintended behaviors, known as "jailbreaks". These jailbreaks are typically triggered by specific text inputs, often referred to as adversarial prompts. In this work, we propose the generation exploitation attack, an extremely simple approach that disrupts model alignment by only manipulating variations of decoding methods. By exploiting different generation strategies, including varying decoding hyper-parameters and sampling methods, we increase the misalignment rate from 0% to more than 95% across 11 language models including LLaMA2, Vicuna, Falcon, and MPT families, outperforming state-of-the-art attacks with 30times lower computational cost. Finally, we propose an effective alignment method that explores diverse generation strategies, which can reasonably reduce the misalignment rate under our attack. Altogether, our study underscores a major failure in current safety evaluation and alignment procedures for open-source LLMs, strongly advocating for more comprehensive red teaming and better alignment before releasing such models. Our code is available at https://github.com/Princeton-SysML/Jailbreak_LLM.

The misuse of large language models (LLMs) has garnered significant attention from the general public and LLM vendors. In response, efforts have been made to align LLMs with human values and intent use. However, a particular type of adversarial prompts, known as jailbreak prompt, has emerged and continuously evolved to bypass the safeguards and elicit harmful content from LLMs. In this paper, we conduct the first measurement study on jailbreak prompts in the wild, with 6,387 prompts collected from four platforms over six months. Leveraging natural language processing technologies and graph-based community detection methods, we discover unique characteristics of jailbreak prompts and their major attack strategies, such as prompt injection and privilege escalation. We also observe that jailbreak prompts increasingly shift from public platforms to private ones, posing new challenges for LLM vendors in proactive detection. To assess the potential harm caused by jailbreak prompts, we create a question set comprising 46,800 samples across 13 forbidden scenarios. Our experiments show that current LLMs and safeguards cannot adequately defend jailbreak prompts in all scenarios. Particularly, we identify two highly effective jailbreak prompts which achieve 0.99 attack success rates on ChatGPT (GPT-3.5) and GPT-4, and they have persisted online for over 100 days. Our work sheds light on the severe and evolving threat landscape of jailbreak prompts. We hope our study can facilitate the research community and LLM vendors in promoting safer and regulated LLMs.

Despite advances in AI alignment, language models (LM) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries modify input prompts to induce harmful behavior. While some defenses have been proposed, they focus on narrow threat models and fall short of a strong defense, which we posit should be effective, universal, and practical. To achieve this, we propose the first adversarial objective for defending LMs against jailbreaking attacks and an algorithm, robust prompt optimization (RPO), that uses gradient-based token optimization to enforce harmless outputs. This results in an easily accessible suffix that significantly improves robustness to both jailbreaks seen during optimization and unknown, held-out jailbreaks, reducing the attack success rate on Starling-7B from 84% to 8.66% across 20 jailbreaks. In addition, we find that RPO has a minor effect on normal LM use, is successful under adaptive attacks, and can transfer to black-box models, reducing the success rate of the strongest attack on GPT-4 from 92% to 6%.

Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in the real world. Prior jailbreak attacks typically rewrite unsafe prompts into paraphrases that evade content filters while preserving meaning. Yet, these approaches often still retain explicit sensitive cues in the input text and therefore overlook a more profound, video-specific weakness. In this paper, we identify a temporal trajectory infilling vulnerability of T2V systems under fragmented prompts: when the prompt specifies only sparse boundary conditions (e.g., start and end frames) and leaves the intermediate evolution underspecified, the model may autonomously reconstruct a plausible trajectory that includes harmful intermediate frames, despite the prompt appearing benign to input or output side filtering. Building on this observation, we propose TFM. This fragmented prompting framework converts an originally unsafe request into a temporally sparse two-frame extraction and further reduces overtly sensitive cues via implicit substitution. Extensive evaluations across multiple open-source and commercial T2V models demonstrate that TFM consistently enhances jailbreak effectiveness, achieving up to a 12% increase in attack success rate on commercial systems. Our findings highlight the need for temporally aware safety mechanisms that account for model-driven completion beyond prompt surface form.

This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to comprehend the text when noise is added to the left side. Motivated by these insights, we propose to disguise the harmful prompt by constructing left-side noise merely based on the prompt itself, then generalize this idea to 4 flipping modes. Second, we verify the strong ability of LLMs to perform the text-flipping task, and then develop 4 variants to guide LLMs to denoise, understand, and execute harmful behaviors accurately. These designs keep FlipAttack universal, stealthy, and simple, allowing it to jailbreak black-box LLMs within only 1 query. Experiments on 8 LLMs demonstrate the superiority of FlipAttack. Remarkably, it achieves sim98\% attack success rate on GPT-4o, and sim98\% bypass rate against 5 guardrail models on average. The codes are available at GitHubhttps://github.com/yueliu1999/FlipAttack.

Understanding the vulnerabilities of Large Vision Language Models (LVLMs) to jailbreak attacks is essential for their responsible real-world deployment. Most previous work requires access to model gradients, or is based on human knowledge (prompt engineering) to complete jailbreak, and they hardly consider the interaction of images and text, resulting in inability to jailbreak in black box scenarios or poor performance. To overcome these limitations, we propose a Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for toxicity maximization, referred to as PBI-Attack. Our method begins by extracting malicious features from a harmful corpus using an alternative LVLM and embedding these features into a benign image as prior information. Subsequently, we enhance these features through bidirectional cross-modal interaction optimization, which iteratively optimizes the bimodal perturbations in an alternating manner through greedy search, aiming to maximize the toxicity of the generated response. The toxicity level is quantified using a well-trained evaluation model. Experiments demonstrate that PBI-Attack outperforms previous state-of-the-art jailbreak methods, achieving an average attack success rate of 92.5% across three open-source LVLMs and around 67.3% on three closed-source LVLMs. Disclaimer: This paper contains potentially disturbing and offensive content.

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box jailbreak methods primarily rely on adversarial textual prompts or image perturbations, yet these approaches are highly detectable by standard content filtering systems and exhibit low query and computational efficiency. In this work, we present Cross-modal Adversarial Multimodal Obfuscation (CAMO), a novel black-box jailbreak attack framework that decomposes malicious prompts into semantically benign visual and textual fragments. By leveraging LVLMs' cross-modal reasoning abilities, CAMO covertly reconstructs harmful instructions through multi-step reasoning, evading conventional detection mechanisms. Our approach supports adjustable reasoning complexity and requires significantly fewer queries than prior attacks, enabling both stealth and efficiency. Comprehensive evaluations conducted on leading LVLMs validate CAMO's effectiveness, showcasing robust performance and strong cross-model transferability. These results underscore significant vulnerabilities in current built-in safety mechanisms, emphasizing an urgent need for advanced, alignment-aware security and safety solutions in vision-language systems.

Large language models (LLMs) have recently experienced tremendous popularity and are widely used from casual conversations to AI-driven programming. However, despite their considerable success, LLMs are not entirely reliable and can give detailed guidance on how to conduct harmful or illegal activities. While safety measures can reduce the risk of such outputs, adversarial jailbreak attacks can still exploit LLMs to produce harmful content. These jailbreak templates are typically manually crafted, making large-scale testing challenging. In this paper, we introduce GPTFuzz, a novel black-box jailbreak fuzzing framework inspired by the AFL fuzzing framework. Instead of manual engineering, GPTFuzz automates the generation of jailbreak templates for red-teaming LLMs. At its core, GPTFuzz starts with human-written templates as initial seeds, then mutates them to produce new templates. We detail three key components of GPTFuzz: a seed selection strategy for balancing efficiency and variability, mutate operators for creating semantically equivalent or similar sentences, and a judgment model to assess the success of a jailbreak attack. We evaluate GPTFuzz against various commercial and open-source LLMs, including ChatGPT, LLaMa-2, and Vicuna, under diverse attack scenarios. Our results indicate that GPTFuzz consistently produces jailbreak templates with a high success rate, surpassing human-crafted templates. Remarkably, GPTFuzz achieves over 90% attack success rates against ChatGPT and Llama-2 models, even with suboptimal initial seed templates. We anticipate that GPTFuzz will be instrumental for researchers and practitioners in examining LLM robustness and will encourage further exploration into enhancing LLM safety.

Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking. As LLMs become more powerful, studying jailbreak methods is critical to enhancing security and aligning models with human values. Traditionally, jailbreak techniques have relied on suffix addition or prompt templates, but these methods suffer from limited attack diversity. This paper introduces DiffusionAttacker, an end-to-end generative approach for jailbreak rewriting inspired by diffusion models. Our method employs a sequence-to-sequence (seq2seq) text diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss. Unlike previous approaches that use autoregressive LLMs to generate jailbreak prompts, which limit the modification of already generated tokens and restrict the rewriting space, DiffusionAttacker utilizes a seq2seq diffusion model, allowing more flexible token modifications. This approach preserves the semantic content of the original prompt while producing harmful content. Additionally, we leverage the Gumbel-Softmax technique to make the sampling process from the diffusion model's output distribution differentiable, eliminating the need for iterative token search. Extensive experiments on Advbench and Harmbench demonstrate that DiffusionAttacker outperforms previous methods across various evaluation metrics, including attack success rate (ASR), fluency, and diversity.

Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break under exploration complexity and intent drift. We propose SEMA, a simple yet effective framework that trains a multi-turn attacker without relying on any existing strategies or external data. SEMA comprises two stages. Prefilling self-tuning enables usable rollouts by fine-tuning on non-refusal, well-structured, multi-turn adversarial prompts that are self-generated with a minimal prefix, thereby stabilizing subsequent learning. Reinforcement learning with intent-drift-aware reward trains the attacker to elicit valid multi-turn adversarial prompts while maintaining the same harmful objective. We anchor harmful intent in multi-turn jailbreaks via an intent-drift-aware reward that combines intent alignment, compliance risk, and level of detail. Our open-loop attack regime avoids dependence on victim feedback, unifies single- and multi-turn settings, and reduces exploration complexity. Across multiple datasets, victim models, and jailbreak judges, our method achieves state-of-the-art (SOTA) attack success rates (ASR), outperforming all single-turn baselines, manually scripted and template-driven multi-turn baselines, as well as our SFT (Supervised Fine-Tuning) and DPO (Direct Preference Optimization) variants. For instance, SEMA performs an average 80.1% ASR@1 across three closed-source and open-source victim models on AdvBench, 33.9% over SOTA. The approach is compact, reproducible, and transfers across targets, providing a stronger and more realistic stress test for large language model (LLM) safety and enabling automatic redteaming to expose and localize failure modes. Our code is available at: https://github.com/fmmarkmq/SEMA.

Large Language Models (LLMs) have shown impressive proficiency across a range of natural language processing tasks yet remain vulnerable to adversarial prompts, known as jailbreak attacks, carefully designed to elicit harmful responses from LLMs. Traditional methods rely on manual heuristics, which suffer from limited generalizability. While being automatic, optimization-based attacks often produce unnatural jailbreak prompts that are easy to detect by safety filters or require high computational overhead due to discrete token optimization. Witnessing the limitations of existing jailbreak methods, we introduce Generative Adversarial Suffix Prompter (GASP), a novel framework that combines human-readable prompt generation with Latent Bayesian Optimization (LBO) to improve adversarial suffix creation in a fully black-box setting. GASP leverages LBO to craft adversarial suffixes by efficiently exploring continuous embedding spaces, gradually optimizing the model to improve attack efficacy while balancing prompt coherence through a targeted iterative refinement procedure. Our experiments show that GASP can generate natural jailbreak prompts, significantly improving attack success rates, reducing training times, and accelerating inference speed, thus making it an efficient and scalable solution for red-teaming LLMs.

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies established by LLM providers. However, the generally broad scope and open-ended nature of existing datasets can complicate the assessment of jailbreaking effectiveness, particularly in specific domains, notably cybersecurity. To address this issue, we present and publicly release CySecBench, a comprehensive dataset containing 12662 prompts specifically designed to evaluate jailbreaking techniques in the cybersecurity domain. The dataset is organized into 10 distinct attack-type categories, featuring close-ended prompts to enable a more consistent and accurate assessment of jailbreaking attempts. Furthermore, we detail our methodology for dataset generation and filtration, which can be adapted to create similar datasets in other domains. To demonstrate the utility of CySecBench, we propose and evaluate a jailbreaking approach based on prompt obfuscation. Our experimental results show that this method successfully elicits harmful content from commercial black-box LLMs, achieving Success Rates (SRs) of 65% with ChatGPT and 88% with Gemini; in contrast, Claude demonstrated greater resilience with a jailbreaking SR of 17%. Compared to existing benchmark approaches, our method shows superior performance, highlighting the value of domain-specific evaluation datasets for assessing LLM security measures. Moreover, when evaluated using prompts from a widely used dataset (i.e., AdvBench), it achieved an SR of 78.5%, higher than the state-of-the-art methods.

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level, model-level, and training-time interventions, followed by three proposed defense strategies. First, a Prompt-Level Defense Framework detects and neutralizes adversarial inputs through sanitization, paraphrasing, and adaptive system guarding. Second, a Logit-Based Steering Defense reinforces refusal behavior through inference-time vector steering in safety-sensitive layers. Third, a Domain-Specific Agent Defense employs the MetaGPT framework to enforce structured, role-based collaboration and domain adherence. Experiments on benchmark datasets show substantial reductions in attack success rate, achieving full mitigation under the agent-based defense. Overall, this study highlights how jailbreaks pose a significant security threat to LLMs and identifies key intervention points for prevention, while noting that defense strategies often involve trade-offs between safety, performance, and scalability. Code is available at: https://github.com/Kuro0911/CS5446-Project

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain vulnerable to jailbreak attacks: carefully crafted image-prompt pairs that compel the model to generate harmful content. In this work, we first highlight a critical safety gap, demonstrating that alignment achieved solely through safety training may be insufficient against jailbreak attacks. To address this vulnerability, we propose Immune, an inference-time defense framework that leverages a safe reward model during decoding to defend against jailbreak attacks. Additionally, we provide a rigorous mathematical characterization of Immune, offering provable guarantees against jailbreaks. Extensive evaluations on diverse jailbreak benchmarks using recent MLLMs reveal that Immune effectively enhances model safety while preserving the model's original capabilities. For instance, against text-based jailbreak attacks on LLaVA-1.6, Immune reduces the attack success rate by 57.82% and 16.78% compared to the base MLLM and state-of-the-art defense strategy, respectively.

Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single target template of "Sure" largely limits the attacking performance of GCG; given this, we propose to apply diverse target templates containing harmful self-suggestion and/or guidance to mislead LLMs. Besides, from the optimization aspects, we propose an automatic multi-coordinate updating strategy in GCG (i.e., adaptively deciding how many tokens to replace in each step) to accelerate convergence, as well as tricks like easy-to-hard initialisation. Then, we combine these improved technologies to develop an efficient jailbreak method, dubbed I-GCG. In our experiments, we evaluate on a series of benchmarks (such as NeurIPS 2023 Red Teaming Track). The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate. The code is released at https://github.com/jiaxiaojunQAQ/I-GCG.

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in red-teaming by probing LLMs to elicit unintended or unsafe behaviors. Recent optimization-based jailbreak approaches iteratively refine attack prompts by leveraging LLMs. However, they often rely heavily on either binary attack success rate (ASR) signals, which are sparse, or manually crafted scoring templates, which introduce human bias and uncertainty in the scoring outcomes. To address these limitations, we introduce AMIS (Align to MISalign), a meta-optimization framework that jointly evolves jailbreak prompts and scoring templates through a bi-level structure. In the inner loop, prompts are refined using fine-grained and dense feedback using a fixed scoring template. In the outer loop, the template is optimized using an ASR alignment score, gradually evolving to better reflect true attack outcomes across queries. This co-optimization process yields progressively stronger jailbreak prompts and more calibrated scoring signals. Evaluations on AdvBench and JBB-Behaviors demonstrate that AMIS achieves state-of-the-art performance, including 88.0% ASR on Claude-3.5-Haiku and 100.0% ASR on Claude-4-Sonnet, outperforming existing baselines by substantial margins.

We investigate long-context vulnerabilities in Large Language Models (LLMs) through Many-Shot Jailbreaking (MSJ). Our experiments utilize context length of up to 128K tokens. Through comprehensive analysis with various many-shot attack settings with different instruction styles, shot density, topic, and format, we reveal that context length is the primary factor determining attack effectiveness. Critically, we find that successful attacks do not require carefully crafted harmful content. Even repetitive shots or random dummy text can circumvent model safety measures, suggesting fundamental limitations in long-context processing capabilities of LLMs. The safety behavior of well-aligned models becomes increasingly inconsistent with longer contexts. These findings highlight significant safety gaps in context expansion capabilities of LLMs, emphasizing the need for new safety mechanisms.

Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from scratch and incrementally refining prompts. However, existing methods suffer from the inefficiency of incremental context construction that requires step-by-step LLM interaction, and often stagnate in suboptimal regions due to surface-level optimization. In this paper, we characterize the Intent-Context Coupling phenomenon, revealing that LLM safety constraints are significantly relaxed when a malicious intent is coupled with a semantically congruent context pattern. Driven by this insight, we propose ICON, an automated multi-turn jailbreak framework that efficiently constructs an authoritative-style context via prior-guided semantic routing. Specifically, ICON first routes the malicious intent to a congruent context pattern (e.g., Scientific Research) and instantiates it into an attack prompt sequence. This sequence progressively builds the authoritative-style context and ultimately elicits prohibited content. In addition, ICON incorporates a Hierarchical Optimization Strategy that combines local prompt refinement with global context switching, preventing the attack from stagnating in ineffective contexts. Experimental results across eight SOTA LLMs demonstrate the effectiveness of ICON, achieving a state-of-the-art average Attack Success Rate (ASR) of 97.1\%. Code is available at https://github.com/xwlin-roy/ICON.

LLMs are known to be vulnerable to jailbreak attacks, even after safety alignment. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses that are rooted in the same harmful knowledge (e.g., detailed steps to make a bomb). Therefore, we conjecture that directly unlearn the harmful knowledge in the LLM can be a more effective way to defend against jailbreak attacks than the mainstream supervised fine-tuning (SFT) based approaches. Our extensive experiments confirmed our insight and suggested surprising generalizability of our unlearning-based approach: using only 20 raw harmful questions without any jailbreak prompt during training, our solution reduced the Attack Success Rate (ASR) in Vicuna-7B on out-of-distribution (OOD) harmful questions wrapped with various complex jailbreak prompts from 82.6\% to 7.7\%. This significantly outperforms Llama2-7B-Chat, which is fine-tuned on about 0.1M safety alignment samples but still has an ASR of 21.9\% even under the help of an additional safety system prompt. Further analysis reveals that the generalization ability of our solution stems from the intrinsic relatedness among harmful responses across harmful questions (e.g., response patterns, shared steps and actions, and similarity among their learned representations in the LLM). Our code is available at https://github.com/thu-coai/SafeUnlearning.

As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect security vulnerabilities in LLMs without manual labor. However, most existing methods struggle to balance the effectiveness and diversity of red-team generated attack prompts. To address this challenge, we propose \ourapproach, a novel automated red teaming training framework that utilizes reinforcement learning to explore and generate more effective attack prompts while balancing their diversity. Specifically, it consists of three training stages: (1) Cold Start: The red team model is supervised and fine-tuned on a jailbreak dataset obtained through imitation learning. (2) Warm-up Exploration: The model is trained in jailbreak instruction following and exploration, using diversity and consistency as reward signals. (3) Enhanced Jailbreak: Progressive jailbreak rewards are introduced to gradually enhance the jailbreak performance of the red-team model. Extensive experiments on a variety of LLMs show that \ourapproach effectively balances the diversity and effectiveness of jailbreak prompts compared to existing methods. Our work significantly improves the efficiency of red team exploration and provides a new perspective on automated red teaming.

As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However, jailbreak attacks, which exploit vulnerabilities to elicit unintended or harmful outputs, threaten LLMs' safety significantly. In this paper, we introduce Layer-AdvPatcher, a novel methodology designed to defend against jailbreak attacks by utilizing an unlearning strategy to patch specific layers within LLMs through self-augmented datasets. Our insight is that certain layer(s), tend to produce affirmative tokens when faced with harmful prompts. By identifying these layers and adversarially exposing them to generate more harmful data, one can understand their inherent and diverse vulnerabilities to attacks. With these exposures, we then "unlearn" these issues, reducing the impact of affirmative tokens and hence minimizing jailbreak risks while keeping the model's responses to safe queries intact. We conduct extensive experiments on two models, four benchmark datasets, and multiple state-of-the-art jailbreak benchmarks to demonstrate the efficacy of our approach. Results indicate that our framework reduces the harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to recent defense methods.

Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition of the issue, we investigate why such attacks succeed and how they can be created. We hypothesize two failure modes of safety training: competing objectives and mismatched generalization. Competing objectives arise when a model's capabilities and safety goals conflict, while mismatched generalization occurs when safety training fails to generalize to a domain for which capabilities exist. We use these failure modes to guide jailbreak design and then evaluate state-of-the-art models, including OpenAI's GPT-4 and Anthropic's Claude v1.3, against both existing and newly designed attacks. We find that vulnerabilities persist despite the extensive red-teaming and safety-training efforts behind these models. Notably, new attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests from the models' red-teaming evaluation sets and outperform existing ad hoc jailbreaks. Our analysis emphasizes the need for safety-capability parity -- that safety mechanisms should be as sophisticated as the underlying model -- and argues against the idea that scaling alone can resolve these safety failure modes.

As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known as jailbreaks. The variety of jailbreak styles is growing, necessitating the use of external defences known as guardrails. While many jailbreak defences have been proposed, not all defences are able to handle new out-of-distribution attacks due to the narrow segment of jailbreaks used to align them. Moreover, the lack of systematisation around defences has created significant gaps in their practical application. In this work, we perform systematic benchmarking across 15 different defences, considering a broad swathe of malicious and benign datasets. We find that there is significant performance variation depending on the style of jailbreak a defence is subject to. Additionally, we show that based on current datasets available for evaluation, simple baselines can display competitive out-of-distribution performance compared to many state-of-the-art defences. Code is available at https://github.com/IBM/Adversarial-Prompt-Evaluation.

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address. First, there is no clear standard of practice regarding jailbreaking evaluation. Second, existing works compute costs and success rates in incomparable ways. And third, numerous works are not reproducible, as they withhold adversarial prompts, involve closed-source code, or rely on evolving proprietary APIs. To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (2) a jailbreaking dataset comprising 100 behaviors -- both original and sourced from prior work -- which align with OpenAI's usage policies; (3) a standardized evaluation framework that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard that tracks the performance of attacks and defenses for various LLMs. We have carefully considered the potential ethical implications of releasing this benchmark, and believe that it will be a net positive for the community. Over time, we will expand and adapt the benchmark to reflect technical and methodological advances in the research community.

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant feature-via prompt-based jailbreaks-can cause alignment to collapse, leading to unsafe generation. Motivated by this, we propose fail-closed alignment as a design principle for robust LLM safety: refusal mechanisms should remain effective even under partial failures via redundant, independent causal pathways. We present a concrete instantiation of this principle: a progressive alignment framework that iteratively identifies and ablates previously learned refusal directions, forcing the model to reconstruct safety along new, independent subspaces. Across four jailbreak attacks, we achieve the strongest overall robustness while mitigating over-refusal and preserving generation quality, with small computational overhead. Our mechanistic analyses confirm that models trained with our method encode multiple, causally independent refusal directions that prompt-based jailbreaks cannot suppress simultaneously, providing empirical support for fail-closed alignment as a principled foundation for robust LLM safety.

Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process. Since proprietary models through API-calling do not grant users such permissions, these attacks find it challenging to compromise them. In this paper, we propose Jailbreaking Using LLM Introspection (JULI), which jailbreaks LLMs by manipulating the token log probabilities, using a tiny plug-in block, BiasNet. JULI relies solely on the knowledge of the target LLM's predicted token log probabilities. It can effectively jailbreak API-calling LLMs under a black-box setting and knowing only top-5 token log probabilities. Our approach demonstrates superior effectiveness, outperforming existing state-of-the-art (SOTA) approaches across multiple metrics.

As large language models~(LLMs) become widely adopted, ensuring their alignment with human values is crucial to prevent jailbreaks where adversaries manipulate models to produce harmful content. While most defenses target single-turn attacks, real-world usage often involves multi-turn dialogues, exposing models to attacks that exploit conversational context to bypass safety measures. We introduce MUSE, a comprehensive framework tackling multi-turn jailbreaks from both attack and defense angles. For attacks, we propose MUSE-A, a method that uses frame semantics and heuristic tree search to explore diverse semantic trajectories. For defense, we present MUSE-D, a fine-grained safety alignment approach that intervenes early in dialogues to reduce vulnerabilities. Extensive experiments on various models show that MUSE effectively identifies and mitigates multi-turn vulnerabilities. Code is available at https://github.com/yansiyu02/MUSE{https://github.com/yansiyu02/MUSE}.

Large language models (LLMs) have demonstrated remarkable capabilities across various applications, highlighting the urgent need for comprehensive safety evaluations. In particular, the enhanced Chinese language proficiency of LLMs, combined with the unique characteristics and complexity of Chinese expressions, has driven the emergence of Chinese-specific benchmarks for safety assessment. However, these benchmarks generally fall short in effectively exposing LLM safety vulnerabilities. To address the gap, we introduce JailBench, the first comprehensive Chinese benchmark for evaluating deep-seated vulnerabilities in LLMs, featuring a refined hierarchical safety taxonomy tailored to the Chinese context. To improve generation efficiency, we employ a novel Automatic Jailbreak Prompt Engineer (AJPE) framework for JailBench construction, which incorporates jailbreak techniques to enhance assessing effectiveness and leverages LLMs to automatically scale up the dataset through context-learning. The proposed JailBench is extensively evaluated over 13 mainstream LLMs and achieves the highest attack success rate against ChatGPT compared to existing Chinese benchmarks, underscoring its efficacy in identifying latent vulnerabilities in LLMs, as well as illustrating the substantial room for improvement in the security and trustworthiness of LLMs within the Chinese context. Our benchmark is publicly available at https://github.com/STAIR-BUPT/JailBench.

With the rise of generative large language models (LLMs) like LLaMA and ChatGPT, these models have significantly transformed daily life and work by providing advanced insights. However, as jailbreak attacks continue to circumvent built-in safety mechanisms, exploiting carefully crafted scenarios or tokens, the safety risks of LLMs have come into focus. While numerous defense strategies--such as prompt detection, modification, and model fine-tuning--have been proposed to counter these attacks, a critical question arises: do these defenses compromise the utility and usability of LLMs for legitimate users? Existing research predominantly focuses on the effectiveness of defense strategies without thoroughly examining their impact on performance, leaving a gap in understanding the trade-offs between LLM safety and performance. Our research addresses this gap by conducting a comprehensive study on the utility degradation, safety elevation, and exaggerated-safety escalation of LLMs with jailbreak defense strategies. We propose USEBench, a novel benchmark designed to evaluate these aspects, along with USEIndex, a comprehensive metric for assessing overall model performance. Through experiments on seven state-of-the-art LLMs, we found that mainstream jailbreak defenses fail to ensure both safety and performance simultaneously. Although model-finetuning performs the best overall, their effectiveness varies across LLMs. Furthermore, vertical comparisons reveal that developers commonly prioritize performance over safety when iterating or fine-tuning their LLMs.

We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token "Sure"), potentially with multiple restarts. In this way, we achieve nearly 100\% attack success rate -- according to GPT-4 as a judge -- on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models -- that do not expose logprobs -- via either a transfer or prefilling attack with 100\% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models -- a task that shares many similarities with jailbreaking -- which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection). We provide the code, prompts, and logs of the attacks at https://github.com/tml-epfl/llm-adaptive-attacks.

The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. However, these large models remain susceptible to jailbreak attacks, where adversaries manipulate prompts to elicit malicious outputs that should not be given by aligned LLMs. Investigating jailbreak prompts can lead us to delve into the limitations of LLMs and further guide us to secure them. Unfortunately, existing jailbreak techniques suffer from either (1) scalability issues, where attacks heavily rely on manual crafting of prompts, or (2) stealthiness problems, as attacks depend on token-based algorithms to generate prompts that are often semantically meaningless, making them susceptible to detection through basic perplexity testing. In light of these challenges, we intend to answer this question: Can we develop an approach that can automatically generate stealthy jailbreak prompts? In this paper, we introduce AutoDAN, a novel jailbreak attack against aligned LLMs. AutoDAN can automatically generate stealthy jailbreak prompts by the carefully designed hierarchical genetic algorithm. Extensive evaluations demonstrate that AutoDAN not only automates the process while preserving semantic meaningfulness, but also demonstrates superior attack strength in cross-model transferability, and cross-sample universality compared with the baseline. Moreover, we also compare AutoDAN with perplexity-based defense methods and show that AutoDAN can bypass them effectively.

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is critical for generalization when attacking models of various sizes. We introduce a novel scalable jailbreak attack that preempts the activation of an LLM's safety policies by occupying its computational resources. Our method involves engaging the LLM in a resource-intensive preliminary task - a Character Map lookup and decoding process - before presenting the target instruction. By saturating the model's processing capacity, we prevent the activation of safety protocols when processing the subsequent instruction. Extensive experiments on state-of-the-art LLMs demonstrate that our method achieves a high success rate in bypassing safety measures without requiring gradient access, manual prompt engineering. We verified our approach offers a scalable attack that quantifies attack strength and adapts to different model scales at the optimal strength. We shows safety policies of LLMs might be more susceptible to resource constraints. Our findings reveal a critical vulnerability in current LLM safety designs, highlighting the need for more robust defense strategies that account for resource-intense condition.

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated adversarial attacks. Existing jailbreak methods typically rely on direct and semantically explicit prompts, overlooking subtle vulnerabilities in how LVLMs compose information over multiple reasoning steps. In this paper, we propose a novel and effective jailbreak framework inspired by Return-Oriented Programming (ROP) techniques from software security. Our approach decomposes a harmful instruction into a sequence of individually benign visual gadgets. A carefully engineered textual prompt directs the sequence of inputs, prompting the model to integrate the benign visual gadgets through its reasoning process to produce a coherent and harmful output. This makes the malicious intent emergent and difficult to detect from any single component. We validate our method through extensive experiments on established benchmarks including SafeBench and MM-SafetyBench, targeting popular LVLMs. Results show that our approach consistently and substantially outperforms existing baselines on state-of-the-art models, achieving near-perfect attack success rates (over 0.90 on SafeBench) and improving ASR by up to 0.39. Our findings reveal a critical and underexplored vulnerability that exploits the compositional reasoning abilities of LVLMs, highlighting the urgent need for defenses that secure the entire reasoning process.

Prior work on jailbreak detection has established the importance of adversarial robustness for LLMs but has largely focused on the model ability to resist adversarial inputs and to output safe content, rather than the effectiveness of external supervision systems. The only public and independent benchmark of these guardrails to date evaluates a narrow set of supervisors on limited scenarios. Consequently, no comprehensive public benchmark yet verifies how well supervision systems from the market perform under realistic, diverse attacks. To address this, we introduce BELLS, a Benchmark for the Evaluation of LLM Supervision Systems. The framework is two dimensional: harm severity (benign, borderline, harmful) and adversarial sophistication (direct vs. jailbreak) and provides a rich dataset covering 3 jailbreak families and 11 harm categories. Our evaluations reveal drastic limitations of specialized supervision systems. While they recognize some known jailbreak patterns, their semantic understanding and generalization capabilities are very limited, sometimes with detection rates close to zero when asking a harmful question directly or with a new jailbreak technique such as base64 encoding. Simply asking generalist LLMs if the user question is "harmful or not" largely outperforms these supervisors from the market according to our BELLS score. But frontier LLMs still suffer from metacognitive incoherence, often responding to queries they correctly identify as harmful (up to 30 percent for Claude 3.7 and greater than 50 percent for Mistral Large). These results suggest that simple scaffolding could significantly improve misuse detection robustness, but more research is needed to assess the tradeoffs of such techniques. Our results support the "bitter lesson" of misuse detection: general capabilities of LLMs are necessary to detect a diverse array of misuses and jailbreaks.

Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model vulnerabilities. However, many existing jailbreak strategies fail to keep pace with the rapid development of defense mechanisms, such as defensive suffixes, rendering them ineffective against defended models. To tackle this issue, we introduce a novel attack method called ArrAttack, specifically designed to target defended LLMs. ArrAttack automatically generates robust jailbreak prompts capable of bypassing various defense measures. This capability is supported by a universal robustness judgment model that, once trained, can perform robustness evaluation for any target model with a wide variety of defenses. By leveraging this model, we can rapidly develop a robust jailbreak prompt generator that efficiently converts malicious input prompts into effective attacks. Extensive evaluations reveal that ArrAttack significantly outperforms existing attack strategies, demonstrating strong transferability across both white-box and black-box models, including GPT-4 and Claude-3. Our work bridges the gap between jailbreak attacks and defenses, providing a fresh perspective on generating robust jailbreak prompts. We make the codebase available at https://github.com/LLBao/ArrAttack.

Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts. While this paradigm greatly expands usability, it also introduces a critical and underexplored safety risk: the attack surface itself becomes visual. In this work, we propose Vision-Centric Jailbreak Attack (VJA), the first visual-to-visual jailbreak attack that conveys malicious instructions purely through visual inputs. To systematically study this emerging threat, we introduce IESBench, a safety-oriented benchmark for image editing models. Extensive experiments on IESBench demonstrate that VJA effectively compromises state-of-the-art commercial models, achieving attack success rates of up to 80.9% on Nano Banana Pro and 70.1% on GPT-Image-1.5. To mitigate this vulnerability, we propose a training-free defense based on introspective multimodal reasoning, which substantially improves the safety of poorly aligned models to a level comparable with commercial systems, without auxiliary guard models and with negligible computational overhead. Our findings expose new vulnerabilities, provide both a benchmark and practical defense to advance safe and trustworthy modern image editing systems. Warning: This paper contains offensive images created by large image editing models.

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them to generate responses to harmful queries. In this study, we propose a new defense mechanism called Context Filtering model, an input pre-processing method designed to filter out untrustworthy and unreliable context while identifying the primary prompts containing the real user intent to uncover concealed malicious intent. Given that enhancing the safety of LLMs often compromises their helpfulness, potentially affecting the experience of benign users, our method aims to improve the safety of the LLMs while preserving their original performance. We evaluate the effectiveness of our model in defending against jailbreak attacks through comparative analysis, comparing our approach with state-of-the-art defense mechanisms against six different attacks and assessing the helpfulness of LLMs under these defenses. Our model demonstrates its ability to reduce the Attack Success Rates of jailbreak attacks by up to 88% while maintaining the original LLMs' performance, achieving state-of-the-art Safety and Helpfulness Product results. Notably, our model is a plug-and-play method that can be applied to all LLMs, including both white-box and black-box models, to enhance their safety without requiring any fine-tuning of the models themselves. We will make our model publicly available for research purposes.

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks, which exploit system vulnerabilities to circumvent safety measures and elicit harmful or inappropriate outputs. Furthermore, while adversarial training-based defense methods have shown promise, a prevalent issue is the unintended over-defense behavior, wherein models excessively reject benign queries, significantly undermining their practical utility. To address these limitations, we introduce LATPC, a Latent-space Adversarial Training with Post-aware Calibration framework. LATPC dynamically identifies safety-critical latent dimensions by contrasting harmful and benign inputs, enabling the adaptive construction of targeted refusal feature removal attacks. This mechanism allows adversarial training to concentrate on real-world jailbreak tactics that disguise harmful queries as benign ones. During inference, LATPC employs an efficient embedding-level calibration mechanism to minimize over-defense behaviors with negligible computational overhead. Experimental results across five types of disguise-based jailbreak attacks demonstrate that LATPC achieves a superior balance between safety and utility compared to existing defense frameworks. Further analysis demonstrates the effectiveness of leveraging safety-critical dimensions in developing robust defense methods against jailbreak attacks.

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts containing rich, implicit cues can induce T2V models to generate semantically unsafe videos that both violate policy and preserve the original (blocked) intent. To realize this, we propose SPARK, a jailbreak framework that leverages T2V models cross-modal associative patterns via a modular prompt design. Specifically, our prompts combine three components: neutral scene anchors, which provide the surface-level scene description extracted from the blocked intent to maintain plausibility; latent auditory triggers, textual descriptions of innocuous-sounding audio events (e.g., creaking, muffled noises) that exploit learned audio-visual co-occurrence priors to bias the model toward particular unsafe visual concepts; and stylistic modulators, cinematic directives (e.g., camera framing, atmosphere) that amplify and stabilize the latent trigger's effect. We formalize attack generation as a constrained optimization over the above modular prompt space and solve it with a guided search procedure that balances stealth and effectiveness. Extensive experiments over 7 T2V models demonstrate the efficacy of our attack, achieving a +23% improvement in average attack success rate in commercial models.

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to adversaries. This work challenges the fundamental differences between unlearning and traditional safety post-training from an adversarial perspective. We demonstrate that existing jailbreak methods, previously reported as ineffective against unlearning, can be successful when applied carefully. Furthermore, we develop a variety of adaptive methods that recover most supposedly unlearned capabilities. For instance, we show that finetuning on 10 unrelated examples or removing specific directions in the activation space can recover most hazardous capabilities for models edited with RMU, a state-of-the-art unlearning method. Our findings challenge the robustness of current unlearning approaches and question their advantages over safety training.

Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain a coherent progression over long interactions, often losing track of what has been accomplished and what remains to be done; they rely on rigid or pre-defined patterns, and fail to adapt to the LLM's dynamic and unpredictable conversational state. To address these shortcomings, we introduce Mastermind, a multi-turn jailbreak framework that adopts a dynamic and self-improving approach. Mastermind operates in a closed loop of planning, execution, and reflection, enabling it to autonomously build and refine its knowledge of model vulnerabilities through interaction. It employs a hierarchical planning architecture that decouples high-level attack objectives from low-level tactical execution, ensuring long-term focus and coherence. This planning is guided by a knowledge repository that autonomously discovers and refines effective attack patterns by reflecting on interactive experiences. Mastermind leverages this accumulated knowledge to dynamically recombine and adapt attack vectors, dramatically improving both effectiveness and resilience. We conduct comprehensive experiments against state-of-the-art models, including GPT-5 and Claude 3.7 Sonnet. The results demonstrate that Mastermind significantly outperforms existing baselines, achieving substantially higher attack success rates and harmfulness ratings. Moreover, our framework exhibits notable resilience against multiple advanced defense mechanisms.

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external tools and can execute multi-stage tasks -- may pose a greater risk if misused, but their robustness remains underexplored. To facilitate research on LLM agent misuse, we propose a new benchmark called AgentHarm. The benchmark includes a diverse set of 110 explicitly malicious agent tasks (440 with augmentations), covering 11 harm categories including fraud, cybercrime, and harassment. In addition to measuring whether models refuse harmful agentic requests, scoring well on AgentHarm requires jailbroken agents to maintain their capabilities following an attack to complete a multi-step task. We evaluate a range of leading LLMs, and find (1) leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking, (2) simple universal jailbreak templates can be adapted to effectively jailbreak agents, and (3) these jailbreaks enable coherent and malicious multi-step agent behavior and retain model capabilities. We publicly release AgentHarm to enable simple and reliable evaluation of attacks and defenses for LLM-based agents. We publicly release the benchmark at https://huggingface.co/ai-safety-institute/AgentHarm.

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and resource-intensive data collection and training processes. In this study, we propose GradSafe, which effectively detects jailbreak prompts by scrutinizing the gradients of safety-critical parameters in LLMs. Our method is grounded in a pivotal observation: the gradients of an LLM's loss for jailbreak prompts paired with compliance response exhibit similar patterns on certain safety-critical parameters. In contrast, safe prompts lead to different gradient patterns. Building on this observation, GradSafe analyzes the gradients from prompts (paired with compliance responses) to accurately detect jailbreak prompts. We show that GradSafe, applied to Llama-2 without further training, outperforms Llama Guard, despite its extensive finetuning with a large dataset, in detecting jailbreak prompts. This superior performance is consistent across both zero-shot and adaptation scenarios, as evidenced by our evaluations on ToxicChat and XSTest. The source code is available at https://github.com/xyq7/GradSafe.

Safety alignment aims to prevent Large Language Models (LLMs) from responding to harmful queries. To strengthen safety protections, jailbreak methods are developed to simulate malicious attacks and uncover vulnerabilities. In this paper, we introduce HILL (Hiding Intention by Learning from LLMs), a novel jailbreak approach that systematically transforms imperative harmful requests into learning-style questions with only straightforward hypotheticality indicators. Further, we introduce two new metrics to thoroughly evaluate the utility of jailbreak methods. Experiments on the AdvBench dataset across a wide range of models demonstrate HILL's strong effectiveness, generalizability, and harmfulness. It achieves top attack success rates on the majority of models and across malicious categories while maintaining high efficiency with concise prompts. Results of various defense methods show the robustness of HILL, with most defenses having mediocre effects or even increasing the attack success rates. Moreover, the assessment on our constructed safe prompts reveals inherent limitations of LLMs' safety mechanisms and flaws in defense methods. This work exposes significant vulnerabilities of safety measures against learning-style elicitation, highlighting a critical challenge of balancing helpfulness and safety alignments.

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing them to conceal their true intentions in a more covert manner. To bridge this gap, we, first, propose a new jailbreak approach, RED QUEEN ATTACK. This method constructs a multi-turn scenario, concealing the malicious intent under the guise of preventing harm. We craft 40 scenarios that vary in turns and select 14 harmful categories to generate 56k multi-turn attack data points. We conduct comprehensive experiments on the RED QUEEN ATTACK with four representative LLM families of different sizes. Our experiments reveal that all LLMs are vulnerable to RED QUEEN ATTACK, reaching 87.62% attack success rate on GPT-4o and 75.4% on Llama3-70B. Further analysis reveals that larger models are more susceptible to the RED QUEEN ATTACK, with multi-turn structures and concealment strategies contributing to its success. To prioritize safety, we introduce a straightforward mitigation strategy called RED QUEEN GUARD, which aligns LLMs to effectively counter adversarial attacks. This approach reduces the attack success rate to below 1% while maintaining the model's performance across standard benchmarks. Full implementation and dataset are publicly accessible at https://github.com/kriti-hippo/red_queen.

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is based on the observation that, even though probabilities of tokens representing harmful contents outweigh those representing harmless responses, safety disclaimers still appear among the top tokens after sorting tokens by probability in descending order. This allows us to mitigate jailbreak attacks by identifying safety disclaimers and amplifying their token probabilities, while simultaneously attenuating the probabilities of token sequences that are aligned with the objectives of jailbreak attacks. We perform extensive experiments on five LLMs using six state-of-the-art jailbreak attacks and four benchmark datasets. Our results show that SafeDecoding significantly reduces the attack success rate and harmfulness of jailbreak attacks without compromising the helpfulness of responses to benign user queries. SafeDecoding outperforms six defense methods.

Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle perturbations to bypass safety mechanisms and trigger harmful outputs. Existing white-box attacks methods require full model accessibility, suffer from computing costs and exhibit insufficient adversarial transferability, making them impractical for real-world, black-box settings. To address these limitations, we propose a black-box jailbreak attack on LVLMs via Zeroth-Order optimization using Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). ZO-SPSA provides three key advantages: (i) gradient-free approximation by input-output interactions without requiring model knowledge, (ii) model-agnostic optimization without the surrogate model and (iii) lower resource requirements with reduced GPU memory consumption. We evaluate ZO-SPSA on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4, achieving the highest jailbreak success rate of 83.0% on InstructBLIP, while maintaining imperceptible perturbations comparable to white-box methods. Moreover, adversarial examples generated from MiniGPT-4 exhibit strong transferability to other LVLMs, with ASR reaching 64.18%. These findings underscore the real-world feasibility of black-box jailbreaks and expose critical weaknesses in the safety mechanisms of current LVLMs

Text-to-Image(T2I) models typically deploy safety filters to prevent the generation of sensitive images. Unfortunately, recent jailbreaking attack methods manually design instructions for the LLM to generate adversarial prompts, which effectively bypass safety filters while producing sensitive images, exposing safety vulnerabilities of T2I models. However, due to the LLM's limited understanding of the T2I model and its safety filters, existing methods require numerous queries to achieve a successful attack, limiting their practical applicability. To address this issue, we propose Reason2Attack(R2A), which aims to enhance the LLM's reasoning capabilities in generating adversarial prompts by incorporating the jailbreaking attack into the post-training process of the LLM. Specifically, we first propose a CoT example synthesis pipeline based on Frame Semantics, which generates adversarial prompts by identifying related terms and corresponding context illustrations. Using CoT examples generated by the pipeline, we fine-tune the LLM to understand the reasoning path and format the output structure. Subsequently, we incorporate the jailbreaking attack task into the reinforcement learning process of the LLM and design an attack process reward that considers prompt length, prompt stealthiness, and prompt effectiveness, aiming to further enhance reasoning accuracy. Extensive experiments on various T2I models show that R2A achieves a better attack success ratio while requiring fewer queries than baselines. Moreover, our adversarial prompts demonstrate strong attack transferability across both open-source and commercial T2I models.

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of alignment failures. In this paper, we propose Alignment-Enhanced Decoding (AED), a novel defense that employs adaptive decoding to address the root causes of jailbreak issues. We first define the Competitive Index to quantify alignment failures and utilize feedback from self-evaluation to compute post-alignment logits. Then, AED adaptively combines AED and post-alignment logits with the original logits to obtain harmless and helpful distributions. Consequently, our method enhances safety alignment while maintaining helpfulness. We conduct experiments across five models and four common jailbreaks, with the results validating the effectiveness of our approach. Code is available at https://github.com/GIGABaozi/AED.git.

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while effective, often depend on input modifications, making them detectable and limiting their stealth and scalability. This paper presents Targeted Model Editing (TME), a novel white-box approach that bypasses safety filters by minimally altering internal model structures while preserving the model's intended functionalities. TME identifies and removes safety-critical transformations (SCTs) embedded in model matrices, enabling malicious queries to bypass restrictions without input modifications. By analyzing distinct activation patterns between safe and unsafe queries, TME isolates and approximates SCTs through an optimization process. Implemented in the D-LLM framework, our method achieves an average Attack Success Rate (ASR) of 84.86% on four mainstream open-source LLMs, maintaining high performance. Unlike existing methods, D-LLM eliminates the need for specific triggers or harmful response collections, offering a stealthier and more effective jailbreak strategy. This work reveals a covert and robust threat vector in LLM security and emphasizes the need for stronger safeguards in model safety alignment.

Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Due to their training on internet-sourced datasets, LLMs can sometimes generate objectionable content, necessitating extensive alignment with human feedback to avoid such outputs. Despite massive alignment efforts, LLMs remain susceptible to adversarial jailbreak attacks, which usually are manipulated prompts designed to circumvent safety mechanisms and elicit harmful responses. Here, we introduce a novel approach, Directed Rrepresentation Optimization Jailbreak (DROJ), which optimizes jailbreak prompts at the embedding level to shift the hidden representations of harmful queries towards directions that are more likely to elicit affirmative responses from the model. Our evaluations on LLaMA-2-7b-chat model show that DROJ achieves a 100\% keyword-based Attack Success Rate (ASR), effectively preventing direct refusals. However, the model occasionally produces repetitive and non-informative responses. To mitigate this, we introduce a helpfulness system prompt that enhances the utility of the model's responses. Our code is available at https://github.com/Leon-Leyang/LLM-Safeguard.

Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability. While many defense methods have been proposed, the trade-offs between safety and helpfulness, and their application to Large Vision-Language Models (LVLMs), are not well understood. This paper systematically examines jailbreak defenses by reframing the standard generation task as a binary classification problem to assess model refusal tendencies for both harmful and benign queries. We identify two key defense mechanisms: safety shift, which increases refusal rates across all queries, and harmfulness discrimination, which improves the model's ability to distinguish between harmful and benign inputs. Using these mechanisms, we develop two ensemble defense strategies-inter-mechanism ensembles and intra-mechanism ensembles-to balance safety and helpfulness. Experiments on the MM-SafetyBench and MOSSBench datasets with LLaVA-1.5 models show that these strategies effectively improve model safety or optimize the trade-off between safety and helpfulness.

Accurately determining whether a jailbreak attempt has succeeded is a fundamental yet unresolved challenge. Existing evaluation methods rely on misaligned proxy indicators or naive holistic judgments. They frequently misinterpret model responses, leading to inconsistent and subjective assessments that misalign with human perception. To address this gap, we introduce JADES (Jailbreak Assessment via Decompositional Scoring), a universal jailbreak evaluation framework. Its key mechanism is to automatically decompose an input harmful question into a set of weighted sub-questions, score each sub-answer, and weight-aggregate the sub-scores into a final decision. JADES also incorporates an optional fact-checking module to strengthen the detection of hallucinations in jailbreak responses. We validate JADES on JailbreakQR, a newly introduced benchmark proposed in this work, consisting of 400 pairs of jailbreak prompts and responses, each meticulously annotated by humans. In a binary setting (success/failure), JADES achieves 98.5% agreement with human evaluators, outperforming strong baselines by over 9%. Re-evaluating five popular attacks on four LLMs reveals substantial overestimation (e.g., LAA's attack success rate on GPT-3.5-Turbo drops from 93% to 69%). Our results show that JADES could deliver accurate, consistent, and interpretable evaluations, providing a reliable basis for measuring future jailbreak attacks.

In recent years, fueled by the rapid advancement of diffusion models, text-to-video (T2V) generation models have achieved remarkable progress, with notable examples including Pika, Luma, Kling, and Open-Sora. Although these models exhibit impressive generative capabilities, they also expose significant security risks due to their vulnerability to jailbreak attacks, where the models are manipulated to produce unsafe content such as pornography, violence, or discrimination. Existing works such as T2VSafetyBench provide preliminary benchmarks for safety evaluation, but lack systematic methods for thoroughly exploring model vulnerabilities. To address this gap, we are the first to formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called T2V-OptJail. This framework consists of two key optimization goals: bypassing the built-in safety filtering mechanisms to increase the attack success rate, preserving semantic consistency between the adversarial prompt and the unsafe input prompt, as well as between the generated video and the unsafe input prompt, to enhance content controllability. In addition, we introduce an iterative optimization strategy guided by prompt variants, where multiple semantically equivalent candidates are generated in each round, and their scores are aggregated to robustly guide the search toward optimal adversarial prompts. We conduct large-scale experiments on several T2V models, covering both open-source models and real commercial closed-source models. The experimental results show that the proposed method improves 11.4% and 10.0% over the existing state-of-the-art method in terms of attack success rate assessed by GPT-4, attack success rate assessed by human accessors, respectively, verifying the significant advantages of the method in terms of attack effectiveness and content control.

The widespread application of large VLMs makes ensuring their secure deployment critical. While recent studies have demonstrated jailbreak attacks on VLMs, existing approaches are limited: they require either white-box access, restricting practicality, or rely on manually crafted patterns, leading to poor sample diversity and scalability. To address these gaps, we propose JPRO, a novel multi-agent collaborative framework designed for automated VLM jailbreaking. It effectively overcomes the shortcomings of prior methods in attack diversity and scalability. Through the coordinated action of four specialized agents and its two core modules: Tactic-Driven Seed Generation and Adaptive Optimization Loop, JPRO generates effective and diverse attack samples. Experimental results show that JPRO achieves over a 60\% attack success rate on multiple advanced VLMs, including GPT-4o, significantly outperforming existing methods. As a black-box attack approach, JPRO not only uncovers critical security vulnerabilities in multimodal models but also offers valuable insights for evaluating and enhancing VLM robustness.

Text-to-image (T2I) models have shown remarkable progress, but their potential to generate harmful content remains a critical concern in the ML community. While various safety mechanisms have been developed, the field lacks systematic tools for evaluating their effectiveness against real-world misuse scenarios. In this work, we propose ICER, a novel red-teaming framework that leverages Large Language Models (LLMs) and a bandit optimization-based algorithm to generate interpretable and semantic meaningful problematic prompts by learning from past successful red-teaming attempts. Our ICER efficiently probes safety mechanisms across different T2I models without requiring internal access or additional training, making it broadly applicable to deployed systems. Through extensive experiments, we demonstrate that ICER significantly outperforms existing prompt attack methods in identifying model vulnerabilities while maintaining high semantic similarity with intended content. By uncovering that successful jailbreaking instances can systematically facilitate the discovery of new vulnerabilities, our work provides crucial insights for developing more robust safety mechanisms in T2I systems.

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignment of LLMs. However, the robustness of these aligned LLMs is always challenged by adversarial attacks that exploit unexplored and underlying vulnerabilities of the safety alignment. In this paper, we develop a novel black-box jailbreak attack, called BitBypass, that leverages hyphen-separated bitstream camouflage for jailbreaking aligned LLMs. This represents a new direction in jailbreaking by exploiting fundamental information representation of data as continuous bits, rather than leveraging prompt engineering or adversarial manipulations. Our evaluation of five state-of-the-art LLMs, namely GPT-4o, Gemini 1.5, Claude 3.5, Llama 3.1, and Mixtral, in adversarial perspective, revealed the capabilities of BitBypass in bypassing their safety alignment and tricking them into generating harmful and unsafe content. Further, we observed that BitBypass outperforms several state-of-the-art jailbreak attacks in terms of stealthiness and attack success. Overall, these results highlights the effectiveness and efficiency of BitBypass in jailbreaking these state-of-the-art LLMs.

Small language models (SLMs) have emerged as promising alternatives to large language models (LLMs) due to their low computational demands, enhanced privacy guarantees and comparable performance in specific domains through light-weight fine-tuning. Deploying SLMs on edge devices, such as smartphones and smart vehicles, has become a growing trend. However, the security implications of SLMs have received less attention than LLMs, particularly regarding jailbreak attacks, which is recognized as one of the top threats of LLMs by the OWASP. In this paper, we conduct the first large-scale empirical study of SLMs' vulnerabilities to jailbreak attacks. Through systematically evaluation on 63 SLMs from 15 mainstream SLM families against 8 state-of-the-art jailbreak methods, we demonstrate that 47.6% of evaluated SLMs show high susceptibility to jailbreak attacks (ASR > 40%) and 38.1% of them can not even resist direct harmful query (ASR > 50%). We further analyze the reasons behind the vulnerabilities and identify four key factors: model size, model architecture, training datasets and training techniques. Moreover, we assess the effectiveness of three prompt-level defense methods and find that none of them achieve perfect performance, with detection accuracy varying across different SLMs and attack methods. Notably, we point out that the inherent security awareness play a critical role in SLM security, and models with strong security awareness could timely terminate unsafe response with little reminder. Building upon the findings, we highlight the urgent need for security-by-design approaches in SLM development and provide valuable insights for building more trustworthy SLM ecosystem.

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can substantially increase jailbreak success rates, exposing a structural cross-lingual security gap. We investigate whether such attacks can be mitigated through language-agnostic semantic similarity without retraining or language-specific adaptation. Our approach compares multilingual query embeddings against a fixed English codebook of jailbreak prompts, operating as a training-free external guardrail for black-box LLMs. We conduct a systematic evaluation across four languages, two translation pipelines, four safety benchmarks, three embedding models, and three target LLMs (Qwen, Llama, GPT-3.5). Our results reveal two distinct regimes of cross-lingual transfer. On curated benchmarks containing canonical jailbreak templates, semantic similarity generalizes reliably across languages, achieving near-perfect separability (AUC up to 0.99) and substantial reductions in absolute attack success rates under strict low-false-positive constraints. However, under distribution shift - on behaviorally diverse and heterogeneous unsafe benchmarks - separability degrades markedly (AUC approx 0.60-0.70), and recall in the security-critical low-FPR regime drops across all embedding models.