English
Related papers

Related papers: AgentHazard: A Benchmark for Evaluating Harmful Be…

200 papers

Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the physical world. Typically, these environments remain unchanged…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Qinhong Zhou , Sunli Chen , Yisong Wang , Haozhe Xu , Weihua Du , Hongxin Zhang , Yilun Du , Joshua B. Tenenbaum , Chuang Gan

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents,…

Cryptography and Security · Computer Science 2025-11-03 Boyi Wei , Benedikt Stroebl , Jiacen Xu , Joie Zhang , Zhou Li , Peter Henderson

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week…

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…

Cryptography and Security · Computer Science 2025-07-30 Gauri Sharma , Vidhi Kulkarni , Miles King , Ken Huang

Computer-use agents (CUAs) that interact with real computer systems can perform automated tasks but face critical safety risks. Ambiguous instructions may trigger harmful actions, and adversarial users can manipulate tool execution to…

Artificial Intelligence · Computer Science 2026-02-04 Tianyu Chen , Chujia Hu , Ge Gao , Dongrui Liu , Xia Hu , Wenjie Wang

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Interactive agent benchmarks face a tension between scalable construction and realistic workflow evaluation. Hand-authored tasks are expensive to extend and revise, while static prompt evaluation misses failures that only appear when agents…

Artificial Intelligence · Computer Science 2026-05-19 Yuxiang Lai , Peng Xia , Haonian Ji , Kaiwen Xiong , Kaide Zeng , Jiaqi Liu , Fang Wu , Jike Zhong , Zeyu Zheng , Cihang Xie , Huaxiu Yao

Large language model (LLM) agents have shown impressive capabilities in human language comprehension and reasoning, yet their potential in cybersecurity remains underexplored. We introduce DefenderBench, a practical, open-source toolkit for…

Computation and Language · Computer Science 2025-10-15 Chiyu Zhang , Marc-Alexandre Cote , Michael Albada , Anush Sankaran , Jack W. Stokes , Tong Wang , Amir Abdi , William Blum , Muhammad Abdul-Mageed

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or…

Cryptography and Security · Computer Science 2026-04-24 Alankrit Chona , Igor Kozlov , Ambuj Kumar

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To…

Software Engineering · Computer Science 2024-11-13 Chengquan Guo , Xun Liu , Chulin Xie , Andy Zhou , Yi Zeng , Zinan Lin , Dawn Song , Bo Li

Large language models (LLMs) are evolving into autonomous decision-makers, raising concerns about catastrophic risks in high-stakes scenarios, particularly in Chemical, Biological, Radiological and Nuclear (CBRN) domains. Based on the…

Computation and Language · Computer Science 2025-03-25 Rongwu Xu , Xiaojian Li , Shuo Chen , Wei Xu

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…

Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. Despite this, these LLM agents introduce unexpected safety risks when operating in interactive environments.…

Computation and Language · Computer Science 2024-10-08 Tongxin Yuan , Zhiwei He , Lingzhong Dong , Yiming Wang , Ruijie Zhao , Tian Xia , Lizhen Xu , Binglin Zhou , Fangqi Li , Zhuosheng Zhang , Rui Wang , Gongshen Liu

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Artificial Intelligence · Computer Science 2025-04-22 Yuting Huang , Leilei Ding , Zhipeng Tang , Tianfu Wang , Xinrui Lin , Wuyang Zhang , Mingxiao Ma , Yanyong Zhang

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

As language models evolve into autonomous agents that act and communicate on behalf of users, ensuring safety in multi-agent ecosystems becomes a central challenge. Interactions between personal assistants and external service providers…

Cryptography and Security · Computer Science 2025-11-10 Amr Gomaa , Ahmed Salem , Sahar Abdelnabi

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

Cryptography and Security · Computer Science 2026-01-16 Yi Liu , Weizhe Wang , Ruitao Feng , Yao Zhang , Guangquan Xu , Gelei Deng , Yuekang Li , Leo Zhang

Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…

Artificial Intelligence · Computer Science 2025-06-05 Yifei Ming , Zixuan Ke , Xuan-Phi Nguyen , Jiayu Wang , Shafiq Joty

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…

Human-Computer Interaction · Computer Science 2026-02-25 Xinfeng Li , Shenyu Dai , Kelong Zheng , Yue Xiao , Gelei Deng , Wei Dong , Xiaofeng Wang

Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task completion. Deployed systems often condition on user profiles or persistent memory, yet agent…

Artificial Intelligence · Computer Science 2026-03-18 Caglar Yildirim