mlsanityData to 14 Oct 2026

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

arXiv 2603.13940 ↗First posted 14 Mar 2026cs.AIcited by 4

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents coordinate via sociological strategies to mislead the system. To address this challenge, we introduce GroupGuard, a training-free defense framework that employs a multi-layered defense strategy, including continuous graph-based monitoring, active honeypot inducement, and structural pruning, to identify and isolate collusive agents. Experimental results across five datasets and four topologies demonstrate that group collusive attacks increase the attack success rate by up to 15% compared to individual attacks. GroupGuard consistently achieves high detection accuracy (up to 88%) and effectively restores collaborative performance, providing a robust solution for securing multi-agent systems.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 21 of its 43 references that are in the map. First posted on arXiv 14 Mar 2026.

Builds on

21 of 43 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Red-Teaming LLM Multi-Agent Systems via Communication Attacks20 Feb
  2. 2025DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent18 Feb
  3. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases17 Jul
  4. 2024BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents5 Jun
  5. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks2 Mar
  6. 2024PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety22 Jan
  7. 2023Evil Geniuses: Delving into the Safety of LLM-based Agents20 Nov
  8. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandbox25 Sep

Other references · 13

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  5. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  6. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  7. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  8. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  9. 2016Solving General Arithmetic Word Problemscited by 360
  10. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  11. 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 147
  12. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 145
1 more
  1. 2023GameGPT: Multi-agent Collaborative Framework for Game Developmentcited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Auditing Agent Harness Safetycited by 11
  2. 2026Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectificationcited by 2
  3. 2026MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systemscited by 0
  4. 2026Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
  2. 2025BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
  3. 2026PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
  4. 2026Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
  5. 2025PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning
  6. 2025MURMUR: Using cross-user chatter to break collaborative language agents in groups
  7. 2025CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
  8. 2025Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems