Related papers: When the Ruler is Broken: Parsing-Induced Suppress…

We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This…

LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, safety, or correctness of generated outputs. While this paradigm has significantly improved the scalability and efficiency of…

As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a…

Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures - a critical functional flaw that undermines their reliability and usability. Current methods…

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…

Cybersecurity is a relentless arms race, with AI driven offensive systems evolving faster than traditional defenses can adapt. Research and tooling remain fragmented across isolated defensive functions, creating blind spots that adversaries…

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert…

Jailbreak vulnerabilities in Large Language Models (LLMs), which exploit meticulously crafted prompts to elicit content that violates service guidelines, have captured the attention of research communities. While model owners can defend…

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

We introduce SOCK, a benchmark command line interface (CLI) that measures large language models' (LLMs) ability to self-replicate without human intervention. In this benchmark, self-replication is defined not only as an LLM's ability to…

Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directly from GitHub, are essential for training machine learning…

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…

Reverse engineering of protocol message formats is critical for many security applications. Mainstream techniques use dynamic analysis and inherit its low-coverage problem -- the inferred message formats only reflect the features of their…

Monitoring issue tracker submissions is a crucial software maintenance activity. A key goal is the prioritization of high risk, security-related bugs. If such bugs can be recognized early, the risk of propagation to dependent products and…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

Inductive reasoning, a cornerstone of human cognition, enables generalization from limited data but hasn't yet been fully achieved by large language models (LLMs). While modern LLMs excel at reasoning tasks, their ability to maintain stable…

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…