Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

Sunwoo Lee, Jaebak Hwang, Yonghyeon Jo, Seungyul Han
2/14/2026

No official code found. Best implementation: sunwoolee0504/WALL (11 stars, Apache-2.0, last commit 2025-12-31).

Abstract

Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation, we propose the Wolfpack Adversarial Attack framework, inspired by wolf hunting strategies, which targets an initial agent and its assisting agents to disrupt cooperation. Additionally, we introduce the Wolfpack-Adversarial Learning for MARL (WALL) framework, which trains robust MARL policies to defend against the proposed Wolfpack attack by fostering systemwide collaboration. Experimental results underscore the devastating impact of the Wolfpack attack and the significant robustness improvements achieved by WALL. Our code is available at https://github.com/sunwoolee0504/WALL.

View on arXivView PDF

Code Implementations(1)

sunwoolee0504/WALLCommunity100%
Apache-2.0
111Shell, PythonMay 20, 20259 months agoApache-2.0

Similar Papers

Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game

88% match1 repo142026

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

88% match2025

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

87% match1 repo52024

Enhancing the Robustness of QMIX against State-adversarial Attacks

85% match2023

Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy

84% match1 repo82023

CAMA: Exploring Collusive Adversarial Attacks in c-MARL

84% match2026

Cite this paper

@article{lee2026wolfpack,
  title  = {Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning},
  author = {Sunwoo Lee and Jaebak Hwang and Yonghyeon Jo and Seungyul Han},
  year   = {2026},
  eprint = {2502.02844},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2502.02844},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.02844.svg)](https://codeofpaper.com/paper/2502.02844)

Discussion