Related papers: MTSA: Multi-turn Safety Alignment for LLMs through…

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Thinking mode has always been regarded as one of the most valuable modes in LLMs. However, we uncover a surprising and previously overlooked phenomenon: LLMs with thinking mode are more easily broken by Jailbreak attack. We evaluate 9 LLMs…

Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) can become a single point of failure when it fails to penalize…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

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 advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We…

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and…

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance…

Despite their staggering capabilities as assistant tools, often exceeding human performances, Large Language Models (LLMs) are still prone to jailbreak attempts from malevolent users. Although red teaming practices have already identified…

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a constrained example-based approach to a more expansive and effective policy-based…

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach creates a mismatch --…

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…