Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

Sunwoo Lee, Jaebak Hwang, Yonghyeon Jo, Seungyul Han
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33025-33056, 2025.

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 system-wide 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-lee25h, title = {Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning}, author = {Lee, Sunwoo and Hwang, Jaebak and Jo, Yonghyeon and Han, Seungyul}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {33025--33056}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/lee25h/lee25h.pdf}, url = {https://proceedings.mlr.press/v267/lee25h.html}, 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 system-wide 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.} }
Endnote
%0 Conference Paper %T Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning %A Sunwoo Lee %A Jaebak Hwang %A Yonghyeon Jo %A Seungyul Han %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-lee25h %I PMLR %P 33025--33056 %U https://proceedings.mlr.press/v267/lee25h.html %V 267 %X 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 system-wide 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.
APA
Lee, S., Hwang, J., Jo, Y. & Han, S.. (2025). Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:33025-33056 Available from https://proceedings.mlr.press/v267/lee25h.html.

Related Material