PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916761491734528 |
|---|---|
| author | Fan, Falong Li, Xi |
| author_facet | Fan, Falong Li, Xi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11642 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Fan, Falong Li, Xi Multiagent Systems Artificial Intelligence Machine Learning 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. |
| title | PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning |
| topic | Multiagent Systems Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.11642 |