paper-with-me

Papers

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

2025-12-01 · Adeela Bashir, The Anh han, Zia Ush Shamszaman 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.

📄 PDF Abstract BibTeX arXiv:2512.03097

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adversarial attacks in consensus-based multi-agent reinforcement learning

2021-03-11 · Martin Figura, Krishna Chaitanya Kosaraju, Vijay Gupta

Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature. In this work, we study the effect of adversarial attacks on a network that employs a conse…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Resilient Finite Time Consensus: A Discontinuous Systems Perspective

2020-03-19

Many algorithms have been proposed in prior literature to guarantee resilient multi-agent consensus in the presence of adversarial attacks or faults. The majority of prior work present excellent results that focus on dis…

An Algorithm For Adversary Aware Decentralized Networked MARL

2023-05-09 · Soumajyoti Sarkar

Decentralized multi-agent reinforcement learning (MARL) algorithms have become popular in the literature since it allows heterogeneous agents to have their own reward functions as opposed to canonical multi-agent Markov …

Multi-agent Reinforcement Learning

Resilient Dynamic Average Consensus based on Trusted agents

2023-03-14 · Shamik Bhattacharyya, Rachel Kalpana Kalaimani

In this paper, we address the discrete-time dynamic average consensus (DAC) of a multi-agent system in the presence of adversarial attacks. The adversarial attack is considered to be of Byzantine type, which compromises …

Adversarial Attack

Multi-Agent Consensus Subject to Communication and Privacy Constraints

2021-02-21 · Dipankar Maity, Panagiotis Tsiotras

We consider a multi-agent consensus problem in the presence of adversarial agents. The adversaries are able to listen to the inter-agent communications and try to estimate the state of the agents. The agents have a limit…

Quantization