Metraipolis › archive › dc_0c4472018ad3
The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection — arXiv:2610.22594
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22594
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:43:28.601Z
- SHA-256 of the archived text
cb1307b25c0704c18bbb086eb59aac385ca21d0105e98e23011255632590eca9- Stable URL of this page
https://metraipolis.com/documento/dc_0c4472018ad3
How to cite
The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection — arXiv:2610.22594 — arXiv (en), https://arxiv.org/abs/2610.22594 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c4472018ad3 (Metraipolis archive dc_0c4472018ad3, sha256 cb1307b25c0704c18bbb086eb59aac385ca21d0105e98e23011255632590eca9)
BibTeX
@misc{dc0c4472018ad3,
title = {The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection — arXiv:2610.22594},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22594},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c4472018ad3; sha256 cb1307b25c0704c18bbb086eb59aac385ca21d0105e98e23011255632590eca9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22594. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical multi-agent systems, in which LLM agents discuss a case, are increasingly studied for clinical decision support. Prompt injection, text that an attacker adds to a model's input, can manipulate LLMs into wrong decisions. How it affects these systems, and how to protect them, remains unclear. Across two systems, two model families and three benchmarks, a single injected passage succeeds in up to 61% of cases, and collaboration does not consistently protect against it. Existing defenses help only partly: they miss injections that look like ordinary clinical text. Yet when asked to check the injected text against the patient's findings, a model that followed the injection usually rejects it. We therefore propose a training-free defense that verifies the clinical judgments behind the system's decision. Following clinical practice, it separates the patient's findings from clinical judgments, such as diagnoses, recommendations and instructions, and checks each judgment against the findings alone, so the decision rests only on supported judgments. Our defense outperforms all baselines on every benchmark, lowering attack success on MedQA to 4-7% while maintaining accuracy on cases without an attack, and remains effective with a medical model and against defense-aware and adaptive attacks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.22594 — 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 2026-10-19T08:39:24.811Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).