Related papers: SafeMLRM: Demystifying Safety in Multi-modal Large…

Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually constructed by distilling safety reasoning traces and answers…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities. We present MIRAGE, a novel multimodal jailbreak…

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety,…

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but…

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce…

While tool learning significantly enhances the capabilities of large language models (LLMs), it also introduces substantial security risks. Prior research has revealed various vulnerabilities in traditional LLMs during tool learning.…

Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue…

Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional defense mechanisms…

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

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…

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

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…