相关论文: When Safety Fails Before the Answer: Benchmarking …

Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite their support capabilities, safe detection and response to crises such as suicidal ideation…

Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include…

Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promising approach to interpreting and monitoring model behaviors. Inspired by the observation that…

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…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns.…

Large reasoning models (LRMs) have achieved impressive performance in complex tasks, often outperforming conventional large language models (LLMs). However, the prevalent issue of overthinking severely limits their computational efficiency.…

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue…

Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy is designed to improve their health outcomes and reduce safety risks. Some large language models (LLMs) have…

Mental health disorders affect hundreds of millions globally, and the Web now serves as a primary medium for accessing support, information, and assessment. Large language models (LLMs) offer scalable and accessible assistance, yet their…

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…

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…

Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where…

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…

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current…

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…