# PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning

arXiv: https://arxiv.org/abs/2505.11642 · HTML: https://mlsanity.com/paper/2505.11642/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 0 of its 36 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Built on by (most cited first, 11 of 11)

- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Web Fraud Attacks Against LLM-Driven Multi-Agent Systems](https://mlsanity.com/paper/2509.01211/) (2025)
- [AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2510.01586/) (2025)
- [Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety](https://mlsanity.com/paper/2508.03864/) (2025)
- [When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems](https://mlsanity.com/paper/2607.11751/) (2026)
- [AutoRAS: Learning Robust Agentic Systems with Primitive Representations](https://mlsanity.com/paper/2606.21445/) (2026)
- [BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placement](https://mlsanity.com/paper/2608.14668/) (2026)
- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)
- [One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs](https://mlsanity.com/paper/2609.18998/) (2026)
- [Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks](https://mlsanity.com/paper/2608.05659/) (2026)
- [AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs](https://mlsanity.com/paper/2609.01023/) (2026)

## Abstract (arXiv)

Multi-agent systems leverage advanced AI models as autonomous agents that interact, cooperate, or compete to complete complex tasks across applications such as robotics and traffic management. Despite their growing importance, safety in multi-agent systems remains largely underexplored, with most research focusing on single AI models rather than interacting agents. This work investigates backdoor vulnerabilities in multi-agent systems and proposes a defense mechanism based on agent interactions. By leveraging reasoning abilities, each agent evaluates responses from others to detect illogical reasoning processes, which indicate poisoned agents. Experiments on LLM-based multi-agent systems, including ChatGPT series and Llama 3, demonstrate the effectiveness of the proposed method, achieving high accuracy in identifying poisoned agents while minimizing false positives on clean agents. We believe this work provides insights into multi-agent system safety and contributes to the development of robust, trustworthy AI interactions.