Multi-Agent System Security

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 112

All topics

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
Aug 4, 2026Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang +3Multi-Agent Collaboration AI Agent Security Benchmarks
Carnegie Mellon University · University of Southern California · Arizona State University
Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity
Aug 4, 2026Anjun Hu, Hanting Xie, Saranya Govindan +2Multi-Agent Systems Recommender Systems
University of Oxford · Amazon
Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach
Aug 3, 2026Mohamed Chahine GhanemAlgorithmic Collusion AI Agent Monitoring
Keele University, Newcastle-Under-Lyme, U.K.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance
Aug 3, 2026Alireza Lotfi, Subangkar Karmaker Shanto, Imtiaz Karim +1AI Agent Security LLM Agent Security
Purdue University · Department of Computer Science · West Lafayette, IN, USA +2
When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems
Aug 2, 2026Jia-Hao Xiao, Lei Feng, Min-Ling ZhangMulti-Agent LLM Systems Backdoor Attacks
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of Computer Network and Information Integration (Southeast University)
MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures
Aug 2, 2026Zhuoning Xu, Xiucheng Zhang, Hanjun Luo +3Multi-Agent Coordination Multi-Agent Orchestration
New York University · New York University Abu Dhabi · The Hong Kong Polytechnic University +1
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
Aug 1, 2026Wenjun Xiong, Yijin Zhou, Jiaqian Wang +6Multi-Agent LLM Systems Agent Memory Poisoning
Shanghai Jiao Tong University · Shanghai Innovation Institute · Xidian University +2
Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking
Jul 31, 2026Yayu Gao, Yong Xiao, Hao Hu +5Cybersecurity AI Agent Security
School of Electronic Information and Communications, the Huazhong University of Science and Technology, Wuhan, China 430074 · Peng Cheng Laboratory, Shenzhen, China · Pazhou Laboratory (Huangpu), Guangzhou, China +4
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Jul 28, 2026Haowen Dai, Zonghao Ying, Wenfeng Li +10AI Agent Safety Information Flow Control
University of Nottingham Ningbo China · Beihang University · Shandong University +6
Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
Jul 27, 2026Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang +1Multi-Agent LLM Systems LLM Backdoor Attacks
Illinois Institute of Technology Chicago, Illinois, USA
Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric
Jul 26, 2026Nikolaos Kekatos, Panagiotis Katsaros, Alexios Lekidis +2Swarm Robotics AI Agent Monitoring
Clone Systems, Larnaca, Cyprus · Aristotle University of Thessaloniki, Thessaloniki, Greece · University of Thessaly, Larissa, Greece
Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions
Jul 14, 2026Huihao Jing, Wenbin Hu, Shaojin Chen +10LLM Agent Security LLM Agent Safety
HKUST · NYU · SWUPL
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
Jul 13, 2026Yibo Hu, Ren WangBackdoor Attacks Backdoor Detection
Illinois Institute of Technology
VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents
Jul 10, 2026Katherine Swinea, Kshitiz Aryal, Lopamudra Praharaj +1Cybersecurity LLM Agent Security
Department of Computer Science, Tennessee Tech University, TN, USA. · School of Interdisciplinary Informatics, University of Nebraska Omaha, NE, USA. · Dept. of Mathematics & Computer Science, University of North Carolina at Pembroke, NC, USA.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
Jul 7, 2026Haowen Xu, Xue Tan, Lei Ma +6LLM Agent Security AI Agent Monitoring
Department of Computer Science, Worcester Polytechnic Institute, MA, USA · School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China +1
CILC: Cryptographically-secure Inter-agent Loop Closure Candidate Detection for Multi-Agent Collaborative SLAM
Jul 7, 2026Andrew Fishberg, Yixuan Jia, Jonathan P. HowSimultaneous Localization and Mapping Secure Multi-Party Computation
Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.
Governed Caste Reassignment in Heterogeneous Swarms: An Asymmetric-Trust Protocol with Audited Operator Countersignature
Jul 6, 2026Xue Qin, Simin Luan, Cong Yang +1Algorithmic Auditing Swarm Robotics
School of Software, Harbin Institute of Technology, Harbin, China. · School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China. · School of Future Science and Engineering, Soochow University, Suzhou, China.
LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems
Jul 5, 2026Yousef Emami, Rahim Taheri, Mohammadhossein Homaei +2Multi-Agent LLM Systems AI Agent Security
Senior Member, IEEE
A Theory of Least Autonomy in AI
Jul 3, 2026Christophe PariselAI Agent Security AI Agent Governance
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
Jun 29, 2026Kunyang Li, Kyle Domico, Jonathan Gregory +1AI Agent Monitoring Multi-Agent System Security
University of Wisconsin–Madison
Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
Jun 29, 2026Dvir Alsheich, Adar Peleg, Ben Hagag +3Adversarial Attacks on LLMs Agent Evaluation
1Technion - Israel Institute of Technology · 2Carnegie Mellon University
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Jun 26, 2026Bo Shen, Lifeng Chang, Tianyuan Wei +7AI Agent Security AI Agent Monitoring
Novo Ordo for AI
Resilient Output Containment under Undisclosed Leader Dynamics and Actuator Attacks
Jun 25, 2026Mohammadreza Nematollahi, Khashayar Khorasani, Nader MeskinCyber-Physical Systems Multi-Agent Control
Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada. · Department of Electrical Engineering, Qatar University, Doha, Qatar.
Governed Shared Memory for Multi-Agent LLM Systems
Jun 23, 2026Yanki Margalit, Nurit Cohen-Inger, Erni Avram +2Multi-Agent LLM Systems Data Provenance
Computer Science and Information, Ben-Gurion University of the Negev
Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response
Jun 16, 2026Raj Patel, Shaswata Mitra, Michele Guida +3Autonomous Cyber Defense AI Agent Safety
The University of Alabama, Alabama, USA · Roma Tre University, Rome, Italy
BARD-MARL: Byzantine-Agent Detection for Learned Communication in Multi-Agent Reinforcement Learning
Jun 15, 2026Almond Kiruthu MurimiMulti-Agent Systems Multi-Agent System Security
Carnegie Mellon University Department of Electrical and Computer Engineering Pittsburgh, Pennsylvania, United States
Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization
Jun 13, 2026Kyle Gao, Pranavi Kotta, Linlin Xu +2Adversarial Robustness LLM Red Teaming
Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada · Department of Mechatronics Engineering, University of Waterloo, Waterloo, ON, Canada · Department of Geomatics Engineering, University of Calgary, Calgary, AB, Canada +1
MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems
Jun 11, 2026Chejian Xu, Zhaorun Chen, Jingyang Zhang +5AI Agent Security Benchmarks Shapley Value Attribution
University of Illinois, Urbana-Champaign · Virtue AI · University of Chicago +3
Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows
Jun 10, 2026Timothy McAllister, Sina Abdidizaji, Ivan Garibay +1AI Agent Security LLM Agent Security
Department of Computer Science, University of Central Florida, Orlando, FL, USA · Department of Industrial Engineering, University of Central Florida, Orlando, FL, USA
SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems
Jun 10, 2026Ruxue Shi, Yili Wang, Mengnan Du +4LLM Agent Security Multi-Agent System Security
School of Artificial Intelligence, Jilin University, Changchun, China · The Chinese University of Hong Kong, Shenzhen, China · School of Information and Communication Technology, Griffith University, Australia

Aug 4, 2026, cs.AIJ/K move · Enter open · S save

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang, Xiyang Hu+2

Carnegie Mellon University · University of Southern California · Arizona State University

Multi-Agent Collaboration AI Agent Security Benchmarks Tool-Using Agents Multi-Agent System Security

Open paper AskPDF arXiv

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmarks study tool use and collaboration, but they do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic user digital workspaces or test how harmful actions can travel through the human-centered agent network. We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints. The benchmark contains 124 base tasks across six cross-user task domains and expands them into 620 scenario variants, with one benign control and four attack-vector variants per base task. The sandbox records peer messages, tool calls, resource operations, governed decisions, and final workspace states. WeClawArena reports utility and attack success rate separately and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.

Momentum

Related topics

Latest papers 112