cs.LGAug 12, 2025

Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning

Authors: Amine Andam, Jamal Bentahar, Mustapha Hedabou

Organizations: Mohammed VI Polytechnic University · Khalifa University · Concordia University

Abstract

Collaborative multi-agent reinforcement learning (MARL) is increasingly deployed in critical domains, yet its vulnerability to adversarial perturbations has not been thoroughly investigated. Most existing adversarial attacks against MARL rely on optimistic assumptions, such as access to policy weights or the ability to train surrogate policies. We investigate whether adversaries with limited capabilities remain effective against MARL agents. In particular, we study two restricted attack settings that are overlooked in the literature: (i) adversaries with access only to agent observations and (ii) adversaries with no access whatsoever. Our approach generates perturbations that intentionally misalign how victim agents perceive their environment, preventing them from collaborating. We conduct extensive experiments across a diverse set of 22 environments. Our results demonstrate both the effectiveness and sample efficiency of our attacks.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CAMA: Exploring Collusive Adversarial Attacks in c-MARL

    Mar 20, 2026Men Niu, Xinxin Fan, Quanliang Jing +2Adversarial AttacksAdversarial MARL

  2. Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning

    May 18, 2026Sunwoo Lee, Mingu Kang, Yonghyeon Jo +1Adversarial TrainingMulti-Agent Coordination

  3. Vulnerability Analysis for Safe Multi-Agent Reinforcement Learning

    Oct 19, 2026Taozheng Zhu, Shixiong Jiang, Fanxin KongSafe MARLAdversarial Attacks