Metraipolis › archive › dc_664aad7d92cd

The Show-Up Attack: When Subagents Win Over Their Supervisor — arXiv:2610.27574

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27574
License (as archived)
CC0-1.0
Archived
2026-10-21T07:06:39.625Z
SHA-256 of the archived text
e8f1716e07157833b811b6ff29644274def83ee967448f3aa1cfdf565ea28966
Stable URL of this page
https://metraipolis.com/documento/dc_664aad7d92cd

How to cite

The Show-Up Attack: When Subagents Win Over Their Supervisor — arXiv:2610.27574 — arXiv (en), https://arxiv.org/abs/2610.27574 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_664aad7d92cd (Metraipolis archive dc_664aad7d92cd, sha256 e8f1716e07157833b811b6ff29644274def83ee967448f3aa1cfdf565ea28966)
BibTeX
@misc{dc664aad7d92cd,
  title = {The Show-Up Attack: When Subagents Win Over Their Supervisor — arXiv:2610.27574},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27574},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_664aad7d92cd; sha256 e8f1716e07157833b811b6ff29644274def83ee967448f3aa1cfdf565ea28966},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27574. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.27574 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-21T07:05:43.423Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).