Related papers: Uncovering Logit Suppression Vulnerabilities in LL…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Large language models (LLMs) have seen widespread success in code generation tasks for different scenarios, both everyday and professional. However current LLMs, despite producing functional code, do not prioritize security and may generate…

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…

As cyber threats continue to grow in complexity, traditional security mechanisms struggle to keep up. Large language models (LLMs) offer significant potential in cybersecurity due to their advanced capabilities in text processing and…

Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic…

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Large Language Models (LLMs) are emerging as transformative tools for software vulnerability detection, addressing critical challenges in the security domain. Traditional methods, such as static and dynamic analysis, often falter due to…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

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…

As Large Language Models are rapidly deployed across diverse applications from healthcare to financial advice, safety evaluation struggles to keep pace. Current benchmarks focus on single-turn interactions with generic policies, failing to…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

This report examines the synergy between Large Language Models (LLMs) and Static Application Security Testing (SAST) to improve vulnerability discovery. Traditional SAST tools, while effective for proactive security, are limited by high…

Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description…

Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially…

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities…

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by…