Multi-Agent System Security

Ask about this topic

Overview

Multi-agent system security examines how agents can attack, mislead, or compromise one another, and how local failures can spread through communication, shared memory, delegated tools, or coordinated decisions. Work studies threats such as prompt injection, collusion, Byzantine behavior, memory poisoning, information leakage, and cascading errors, using settings from language-model workflows and debate to multi-agent reinforcement learning and robot swarms. Defenses include trust and reputation systems, provenance and authorization controls, runtime monitoring, semantic information-flow checks, and cryptographic protocols; benchmarks increasingly test different architectures, interaction paths, and long-horizon tasks. A central challenge is that safeguards effective for individual agents may not compose at system level, while stronger controls can reduce task performance or miss attacks that emerge only through multi-agent interaction.

Latest papers

CardsList

181 papers29 papers in the last four weeks, up 12% on the four weeks before. 0.2% of all new papers.

  1. Agents for Agents: An Interrogator-Based Secure Framework for Autonomous Internet of Underwater Things

    Apr 5, 2026Ali Akarma, Toqeer Ali Syed, Abdul Khadar Jilani +4Multi-Agent System SecurityInternet of Things

    AI Center, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia · College of Computer Studies, University of Technology Bahrain, Sitra 18041, Bahrain · Faculty of Computer Studies, Arab Open University-Bahrain, Manama 32038, Bahrain +3

  2. SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

    Apr 3, 2026KrishnaSaiReddy PatilAI Agent GovernanceMulti-Agent System Security

  3. Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

    Apr 1, 2026Aaron Rose, Carissa Cullen, Sahar Abdelnabi +3AI Agent Security BenchmarksMulti-Agent System Security

    University of Oxford · ELLIS Institute Tübingen · Witt Lab University of Oxford +1

  4. Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems

    Mar 30, 2026Yicheng Cai, Mitchell John DeStefano, Guodong Dong +5AI Agent Security BenchmarksCybersecurity

    Cyber Security Laboratory Pennsylvania State University, University Park

  5. Emergent Risks in Generative Multi-Agent Systems

    Mar 29, 2026Yue Huang, Yu Jiang, Wenjie Wang +12Multi-Agent LLM SystemsMulti-Agent Systems

    University of Notre Dame · LMU Munich · University of Washington +7

  6. From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies

    Mar 26, 2026Anbang RuanAI Agent GovernanceMulti-Agent Systems

    NetX Foundation

  7. Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions

    Mar 22, 2026Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1Multi-Agent System SecurityMulti-Agent Communication

    Lancaster University, Lancaster, United Kingdom

  8. CAMA: Exploring Collusive Adversarial Attacks in c-MARL

    Mar 20, 2026Men Niu, Xinxin Fan, Quanliang Jing +2Adversarial AttacksAdversarial MARL

    Institute of Computing Technology, CAS · UCAS · Beihang University

  9. Memory poisoning and secure multi-agent systems

    Mar 20, 2026Vicenç Torra, Maria Bras-AmorósAgent Memory PoisoningAI Agent Security

    Department of Computing Science, Umeå University, Umeå, Sweden. · Departament of Mathematics, Universitat Politècnica de Catalunya, Catalonia, Spain.

  10. TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems

    Mar 19, 2026Volodymyr SeliuchenkoAgent ReliabilityMulti-Agent System Security

  11. Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks

    Mar 16, 2026Samira Abedini, Sina Mavali, Lea Schönherr +2Multi-Agent LLM SystemsLLM Agent Security

    CISPA Helmholtz Center for Information Security · University of Vienna, Faculty of Computer Science

  12. AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

    Mar 16, 2026Yihao Zhang, Zeming Wei, Xiaokun Luan +7LLM Agent SecurityMulti-Agent System Security

    Peking University · Sun Yat-sen University · Wuhan University +2

  13. TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems

    Mar 16, 2026Kai Wang, Biaojie Zeng, Zeming Wei +7LLM Agent SafetyMulti-Agent System Security

    Shanghai AI Laboratory

  14. GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems

    Mar 14, 2026Yiling Tao, Xinran Zheng, Shuo Yang +2Graph-Based Anomaly DetectionLLM Agent Security

    Shenzhen International Graduate School, Tsinghua University · Department of Electrical and Electronic Engineering, The University of Hong Kong · School of Computer Science and Engineering, University of Electronic Science and Technology of China

  15. Security Considerations for Artificial Intelligence Agents

    Mar 12, 2026Ninghui Li, Kaiyuan Zhang, Kyle Polley +1AI Agent SecurityLLM Agent Security

    Perplexity · Purdue University

  16. Quantum-Secure-By-Construction (QSC): A Paradigm Shift For Post-Quantum Agentic Intelligence

    Mar 12, 2026Arit Kumar Bishwas, Mousumi Sen, Albert Nieto-Morales +1Multi-Agent System Security

    PricewaterhouseCoopers USA, San Francisco, CA · Independent Researcher, USA, Fremont, CA

  17. WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

    Mar 11, 2026Zixun Xiong, Gaoyi Wu, Lingfeng Yao +3Multi-Agent System SecurityMulti-Agent LLM Systems

    Department of Electrical and Computer Engineering, Stevens Institute of Technology · Department of Electrical and Computer Engineering, University of Houston

  18. AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations

    Mar 10, 2026Shaswata Mitra, Raj Patel, Sudip Mittal +2AI Agent SecurityMulti-Agent System Security

    Department of Computer Science, The University of Alabama, Tuscaloosa, USA

  19. Security Considerations for Multi-agent Systems

    Mar 9, 2026Tam Nguyen, Moses Ndebugre, Dheeraj ArremsettyAI Agent SecurityMulti-Agent System Security

    Crew Scaler · North Carolina A&T State University

  20. DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs

    Mar 9, 2026Yu Li, Qiang Hu, Yao Zhang +3AI Agent SecurityLLM Agent Security

    Tianjin University · Singapore Management University

  21. From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents

    Mar 8, 2026Xiaolei Zhang, Lu Zhou, Xiaogang Xu +5AI Agent SecurityLLM Agent Security

    Nanjing University of Aeronautics and Astronautics, China · Collaborative Innovation Center of Novel Software Technology and Industrialization, China · The Chinese University of Hong Kong, China +6

  22. Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution

    Mar 4, 2026Zixun Luo, Yuhang Fan, Hengyu Lin +2Ollivier-Ricci CurvatureMulti-Agent LLM Systems

    Huazhong University of Science and Technology · Lingnan University · Tsinghua University +1

  23. From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

    Mar 4, 2026Yizhe Xie, Congcong Zhu, Xinyue Zhang +5Multi-Agent LLM SystemsMulti-Agent Systems

    Faculty of Data Science, City University of Macau · Minzu University of China

  24. Cross-Layer Semantic Flow Reconstruction for Attack Detection in Agentic Systems

    Mar 4, 2026Qizhi Cai, Yangyang Wei, Zhipeng Chen +2AI Agent SecurityLLM Agent Security

    Department of Software Technology, Zhejiang University, Ningbo, China · Department of Computer Science and Technology, Zhejiang University, Hangzhou, China

  25. Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems

    Feb 23, 2026Moritz Weckbecker, Jonas Müller, Ben Hagag +1Multi-Agent System SecurityMulti-Agent Systems

    Fraunhofer HHI, Berlin, Germany · Eleuther AI · TU Berlin, Berlin, Germany +2

  26. Graph-theoretic Agreement Framework for Multi-agent LLM Systems

    Feb 23, 2026Muhammad Umar JavedMulti-Agent LLM SystemsMulti-Agent Consensus

  27. Formal Policy Enforcement for Agentic Systems

    Feb 18, 2026Nils Palumbo, Sarthak Choudhary, Jihye Choi +4Runtime Enforcement for AI AgentsAI Agent Governance

    University of Wisconsin–Madison · Cornell University · Langroid

  28. Secure and Energy-Efficient Wireless Agentic AI Networks

    Feb 16, 2026Yuanyan Song, Kezhi Wang, Xinmian XuWireless Resource AllocationWireless Communications

    Department of Computer Science, Brunel University of London, UB8 3PH, UK · Nanjing University of Posts and Telecommunications

  29. MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS

    Nov 28, 2025Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov +8Multi-Agent LLM SystemsLLM Auditing

    Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240, China

  30. Seven Security Challenges in Cross-domain Multi-agent LLM Systems

    May 28, 2025Ronny Ko, Jiseong Jeong, Shuyuan Zheng +4Multi-Agent LLM SystemsLLM Agent Security

    Osaka University · Seoul National University · Yonsei University