Related papers: Expected Harm: Rethinking Safety Evaluation of (Mi…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts often overlook attacks that exploit the model's capacity for…

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can…

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing…

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's…

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

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…

Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabilities, behavioral profile, and internal failure mode. We study behavioral and mechanistic…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced LLMs are designed…

Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have gained significant attention due to their objective and verifiable reward signals, demonstrating strong performance in reasoning and code generation tasks.…

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges…

Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech. Countermeasures,…

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…