Related papers: HauntAttack: When Attack Follows Reasoning as a Sh…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on…

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that "think then act." However, recent observations, like OpenAI's o3, suggest a paradox: stronger reasoning often coincides with…

Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of…

Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking attacks. Although various advanced methods have been…

Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential…

Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where…

The widespread adoption of thinking mode in large language models (LLMs) has significantly enhanced complex task processing capabilities while introducing new security risks. When subjected to jailbreak attacks, the step-by-step reasoning…

Large Reasoning Models (LRMs) excel at complex reasoning but are traditionally evaluated in static, "frozen world" settings: model responses are assumed to be instantaneous, and the context of a request is presumed to be immutable over the…

Large reasoning models (LRMs) have shown remarkable progress on complex reasoning tasks. However, some questions posed to LRMs are inherently unanswerable, such as math problems lacking sufficient conditions. We find that LRMs continually…

Recent advances in Chain-of-Thought (CoT) prompting have substantially enhanced the reasoning capabilities of large language models (LLMs), enabling sophisticated problem-solving through explicit multi-step reasoning traces. However, these…

With the growing accessibility and wide adoption of large language models, concerns about their safety and alignment with human values have become paramount. In this paper, we identify a concerning phenomenon: Reasoning-Induced Misalignment…

Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechanisms and lead MLLMs…

Recent Large Reasoning Models (LRMs) excel at complex reasoning tasks but often suffer from overthinking, generating overly long and redundant reasoning trajectories. To explore its essence, our empirical analysis reveals that LRMs are…

With the widespread real-world deployment of large language models (LLMs), ensuring their behavior complies with safety standards has become crucial. Jailbreak attacks exploit vulnerabilities in LLMs to induce undesirable behavior, posing a…

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more readily with harmful prompts if real-world consequences…