Related papers: LLM-VA: Resolving the Jailbreak-Overrefusal Trade-…

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

As vision-language models (VLMs) become increasingly capable, maintaining a balance between safety and usefulness remains a central challenge. Safety mechanisms, while essential, can backfire, causing over-refusal, where models decline…

Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as existing methods like Reinforcement Learning from Human Feedback (RLHF) often handle only coarse-grained attributes. In practice, fine-tuning…

Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants; however, they pose increasing safety risks. How can we ensure safety alignment of MLLMs to prevent undesired behaviors? Going further, it is…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

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…

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

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…

As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…

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…

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…