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

arXiv: https://arxiv.org/abs/2512.03097 · HTML: https://mlsanity.com/paper/2512.03097/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 17 of 17)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025)
- [GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion](https://mlsanity.com/paper/2409.14051/) (2024)
- [LLM Voting: Human Choices and AI Collective Decision Making](https://mlsanity.com/paper/2402.01766/) (2024)
- [The Traitors: Deception and Trust in Multi-Agent Language Model Simulations](https://mlsanity.com/paper/2505.12923/) (2025)
- [Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents](https://mlsanity.com/paper/2504.08640/) (2025)
- [Evaluating LLM Agent Collusion in Double Auctions](https://mlsanity.com/paper/2507.01413/) (2025)
- [Reliable and Resilient AI and IoT-based Personalised Healthcare Services: A Survey](https://mlsanity.com/paper/2209.05457/) (2022)

## Built on by (most cited first, 3 of 3)

- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)
- [One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs](https://mlsanity.com/paper/2609.18998/) (2026)
- [The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI](https://mlsanity.com/paper/2607.19433/) (2026)

## Abstract (arXiv)

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.