Skip to main navigation Skip to search Skip to main content

Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare

Research output: Working paperPreprint

Abstract

The integration of large language models (LLMs) into healthcare IoT systems promises faster decisions and improved medical support. LLMs are also deployed as multi-agent teams to assist AI doctors by debating, voting, or advising on decisions. However, when multiple assistant agents interact, coordinated adversaries can collude to create false consensus, pushing an AI doctor toward harmful prescriptions. We develop an experimental framework with scripted and unscripted doctor agents, adversarial assistants, and a verifier agent that checks decisions against clinical guidelines. Using 50 representative clinical questions, we find that collusion drives the Attack Success Rate (ASR) and Harmful Recommendation Rates (HRR) up to 100% in unprotected systems. In contrast, the verifier agent restores 100% accuracy by blocking adversarial consensus. This work provides the first systematic evidence of collusion risk in AI healthcare and demonstrates a practical, lightweight defence that ensures guideline fidelity.
Original languageEnglish
PublisherarXiv
Number of pages7
DOIs
Publication statusPublished - 1 Dec 2025

Publication series

Name
ISSN (Electronic)2331-8422

Bibliographical note

7 pages Conference level paper

Fingerprint

Dive into the research topics of 'Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare'. Together they form a unique fingerprint.

Cite this