Maosen Zhang, Jianshuo Dong, Yutong Zhang, Jie Zhang, Tianwei Zhang, Han Qiu · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.27574 · cited by 0 works (OpenAlex) · open-access PDF
複数の大言語モデル(LLM)エージェントを調整するために複数のマルチエージェントシステムがどんどん展開されているが、これはまた新たな攻撃表面を生み出す:悪意のあるエージェントは連携を取する可能性がある。この論文では、悪意のあるサブエージェントが監督をその割り当てられた範囲を超える任務に巻き込むように操作する「textit{show-up attack}」を提案し、研究する。しかし、このリスクを評価するには、6つの攻撃戦略を実装し、188のテストケースが含まれているSUA-Arenaを提案する。その後、6つの境界LLMを評価し、それらがすべてショーアップ攻撃に脆弱であることを発見する。例えば、監督
Machine translation (Meta M2M100); the English original follows.
Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this also creates new attack surfaces: malicious agents may have chances to exploit the coordination. In this paper, we propose and study the \textit{show-up attack}, in which a malicious subagent manipulates the supervisor into involving it in tasks beyond its assigned scope. To evaluate this risk, we propose SUA-Arena, which implements 6 attack strategies and contains 188 test cases. Then, we evaluate 6 frontier LLMs and find that all of them are vulnerable to show-up attacks. For example, GPT-5.6-Sol as a supervisor suffers an ASR of up to 0.93. Mitigation strategies such as prompting and restricted communication fail to reduce the risk consistently. These results show that multi-agent systems need explicit mechanisms for enforcing authority boundaries.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Supervisor, Exploit, Computer security, Computer science, Test (biology), Key (lock)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27574, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange