Computer-Use Agent Safety

Ask about this topic

Latest papers

CardsList

20 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

  1. Towards Safe Autonomy for Computer Use

    Oct 13, 2026Dominik Seip, Bartol Markovinović, Matthias HeinComputer-Use Agent SafetyAI Agent Safety

    Tübingen AI Center, University of Tübingen

  2. AgentSpy: Making AI Agent Behavior Observable

    Oct 5, 2026Christoph Bühler, Matteo Biagiola, Luca Di Grazia +1AI Agent ReliabilityAI Agent Auditing

    University of St. Gallen, St. Gallen, SG, Switzerland · University of St. Gallen and Università della Svizzera italiana (USI), St. Gallen and Lugano, SG and TI, Switzerland

  3. SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety

    Sep 28, 2026Jianxing Chen, Xiao Yu, Shipra Agrawal +1Computer-Use Agent SafetyAI Agent Safety

    Columbia University

  4. HazardAuditor: From Executable Threats to Safer Computer-Use Agents

    Sep 14, 2026Yunhao Feng, Ruixiao Lin, Ming Wen +5Computer-Use Agent SafetyLanguage Model Safety Evaluation

    Ant Group · Hunan Institute of Advanced Technology · Zhejiang University +3

  5. Beyond Task Completion: Training Capable and Safe Computer-Use Agents

    Aug 27, 2026Zeyu Kang, Zhenyun Yin, Yang Zhang +5Computer-Use Agent SafetyComputer-Use Agents

    Shanghai Artificial Intelligence Laboratory · Harbin Institute of Technology · Fudan University +2

  6. ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices

    Aug 25, 2026Joy Chen, Alejandro Castillejo Munoz, Pierluca D'Oro +3Computer-Use Agent BenchmarksComputer-Use Agent Evaluation

    FAIR at Meta

  7. The Compaction Cliff in Long-Running AI Agent Memory

    Aug 24, 2026Saber Zerhoudi, Jelena Mitrovic, Michael GranitzerLLM Agent MemoryAgent Memory Management

    University of Passau Passau, Germany · IT:U Linz, Austria

  8. Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

    Aug 3, 2026Jia-Chen Zhang, Ze-Yu Zhang, Kai-Wei ZhangComputer-Use Agent SafetyAI Agent Security Benchmarks

    1East China Normal University · 2Shanghai Jiao Tong University · 3Shanghai AI Laboratory

  9. Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?

    Jun 22, 2026Anmol Goel, Iryna GurevychComputer-Use AgentsContextual Integrity

    Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE

  10. OSGuard: A Benchmark for Safety in Computer-Use Agents

    Jun 13, 2026Mina Mohammadmirzaei, Jeffrey FlaniganComputer-Use Agent SafetyComputer-Use Agents

    University of California, Santa Cruz

  11. MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

    Jun 2, 2026Jia Yu, Zilong Wang, Xinyang Jiang +2LLM Agent EvaluationAI Agent Benchmarks

    Microsoft Research Asia, Shanghai, China · Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China · Shanghai Key Laboratory of MICCAI, Shanghai, China

  12. BraveGuard: From Open-World Threats to Safer Computer-Use Agents

    May 31, 2026Yunhao Feng, Xiaohu Du, Xinhao Deng +13Computer-Use Agent SafetyLLM Guardrails

    1Fudan University · Ant Group · 8ShanghaiUniversity +5

  13. Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

    May 18, 2026Yubin Qu, Ying Zhang, Yanjun Zhang +4Tool Access Control for LLM AgentsComputer-Use Agent Benchmarks

    Griffith University · Wake Forest University · Nanyang Technological University +2

  14. Human-Guided Harm Recovery for Computer Use Agents

    Apr 20, 2026Christy Li, Sky CH-Wang, Andi Peng +1Computer-Use AgentsAI Agent Security Benchmarks

    MIT CSAIL · Abridge · humans&

  15. The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

    Apr 12, 2026Xuwei Ding, Skylar Zhai, Linxin Song +6Computer-Use Agent SafetyAI Agent Safety

    University of Wisconsin–Madison · University of Minnesota · University of Southern California +3

  16. AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents

    Apr 3, 2026Yunhao Feng, Yifan Ding, Yingshui Tan +6LLM Safety BenchmarksComputer-Use Agent Benchmarks

    Alibaba Group · Fudan University · Hunan Institute of Advanced Technology +2

  17. "What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents

    Mar 30, 2026Zifan Peng, Mingchen LiComputer-Use Agent SafetyComputer-Use Agents

    The Hong Kong University of Science and Technology (Guangzhou), China · University of North Texas, The United States

  18. Agent-Sentry: Bounding LLM Agents via Execution Provenance

    Mar 24, 2026Rohan Sequeira, Stavros Damianakis, Umar Iqbal +1Computer-Use Agent SafetyAI Agent Security

    University of Southern California, Los Angeles, California, USA · Washington University in St. Louis, St. Louis, Missouri, USA

  19. Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents

    Mar 16, 2026Xunzhuo Liu, Bowei He, Xue Liu +3Computer-Use Agent SafetyAI Agent Security

    vLLM Semantic Router Project · MBZUAI · McGill University +2

  20. Measuring Harmfulness of Computer-Using Agents

    Jul 31, 2025Aaron Xuxiang Tian, Ruofan Zhang, Janet Tang +3LLM Agent SafetyComputer-Use Agent Benchmarks

    Independent Researcher · Arizona State University · Gradient +1