Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914413583269888 |
|---|---|
| author | Xiang, Qiuchi Qu, Haoxuan Rahmani, Hossein Liu, Jun |
| author_facet | Xiang, Qiuchi Qu, Haoxuan Rahmani, Hossein Liu, Jun |
| contents | Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely unexplored attack scenario, the discussion-monitored scenario, where anomaly detectors continuously monitor inter-agent communications and block detected adversarial messages. Although existing attacks are effective without discussion monitoring, we show that they exhibit detectable patterns and largely fail under such monitoring constraints. But does this imply that monitoring alone is sufficient to secure multi-agent discussions? To answer this question, we develop a novel attack method explicitly tailored to the discussion-monitored scenario. Extensive experiments demonstrate that effective attacks remain possible even under continuous monitoring, indicating that monitoring alone does not eliminate adversarial risks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21194 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions Xiang, Qiuchi Qu, Haoxuan Rahmani, Hossein Liu, Jun Cryptography and Security Artificial Intelligence Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely unexplored attack scenario, the discussion-monitored scenario, where anomaly detectors continuously monitor inter-agent communications and block detected adversarial messages. Although existing attacks are effective without discussion monitoring, we show that they exhibit detectable patterns and largely fail under such monitoring constraints. But does this imply that monitoring alone is sufficient to secure multi-agent discussions? To answer this question, we develop a novel attack method explicitly tailored to the discussion-monitored scenario. Extensive experiments demonstrate that effective attacks remain possible even under continuous monitoring, indicating that monitoring alone does not eliminate adversarial risks. |
| title | Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2603.21194 |