Related papers: CTFExplorer: Evaluating LLM Offensive Agents Throu…

Characterizing attacker behavior with respect to Cyber-Physical Systems is important to assuring the security posture and resilience of these systems. Classical cyber vulnerability assessment approaches rely on the knowledge and experience…

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a…

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Security Operation Centers) analysts are often…

LLM agents are emerging as a key enabler for autonomous wireless network management. Reliably deploying them, however, demands benchmarks that reflect real engineering risk. Existing wireless benchmarks evaluate single isolated capabilities…

Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-specific information. We identify autonomous exploration as…

Team collaboration among individuals with diverse sets of expertise and skills is essential for solving complex problems. As part of an interdisciplinary effort, we studied the effects of Capture the Flag (CTF) game, a popular and engaging…

Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas, and dispatch structure but never sees an engine-level…

The prospect of artificial intelligence (AI) competing in the adversarial landscape of cyber security has long been considered one of the most impactful, challenging, and potentially dangerous applications of AI. Here, we demonstrate a new…

Rooted in collaborative efforts, cybersecurity spans the scope of cyber competitions and warfare. Despite extensive research into team strategy in sports and project management, empirical study in cyber-security is minimal. This gap…

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

This, with the ever-increasing sophistication of cyberwar, calls for novel solutions. In this regard, Large Language Models (LLMs) have emerged as a highly promising tool for defensive and offensive cybersecurity-related strategies. While…

Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable…

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…

Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled…

The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…

The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature…

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…