相关论文: Catastrophic Cyber Capabilities Benchmark (3CB): R…

Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…

Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence,…

Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety constraint: the performance is not worse than a baseline policy…

The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, principally hallucination, fails to adequately characterize. This paper introduces LLM Psychosis…

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 shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination…

Critique ability, i.e., the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalable oversight. While numerous studies have been proposed to…

LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners. Here, we present an open-source evaluation framework and benchmark…

Large language models and LLM-based agents are increasingly used for cybersecurity tasks that are inherently dual-use. Existing approaches to refusal, spanning academic policy frameworks and commercially deployed systems, often rely on…

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Existing threat modeling frameworks related to transportation cyber-physical systems (CPS) are often narrow in scope, labor-intensive, and require substantial cybersecurity expertise. To this end, we introduce the Transportation…

The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However, current benchmarks primarily report final accuracy, revealing what models can do but…

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

The assessment of cybersecurity Capture-The-Flag (CTF) exercises involves participants finding text strings or ``flags'' by exploiting system vulnerabilities. Large Language Models (LLMs) are natural-language models trained on vast amounts…

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…

Agentic systems involved in high-stake decision-making under adversarial pressure need formal guarantees not offered by existing approaches. Motivated by the operational needs of security operations centers (SOCs) that must configure…

LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, and the agent must robustly follow that intent even when…

Existing language model safety evaluations focus on overt attacks and low-stakes tasks. In reality, an attacker can easily subvert existing safeguards by requesting help on small, benign-seeming tasks across many independent queries.…

With the emergence of high-performance large language models (LLMs) such as GPT, Claude, and Gemini, the autonomous and semi-autonomous execution of tasks has significantly advanced across various domains. However, in highly specialized…