Mixed Nash for Robust Federated Learning

Wanyun Xie, Thomas Pethick, Ali Ramezani-Kebrya, Volkan Cevher

Abstract: We study robust federated learning (FL) within a game theoretic framework to alleviate the server vulnerabilities to even an informed adversary who can tailor training-time attacks. Specifically, we introduce RobustTailor, a simulation-based framework that prevents the adversary from being omniscient and derives its convergence guarantees. RobustTailor improves robustness to training-time attacks significantly while preserving almost the same privacy guarantees as standard robust aggregation schemes in FL. Empirical results under challenging attacks show that RobustTailor performs close to an upper bound with perfect knowledge of honest clients.

Submission Length: Regular submission (no more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=BhuXZ2DSbx

Changes Since Last Submission: Final version.

Assigned Action Editor: ~Aurélien_Bellet1

License: Creative Commons Attribution 4.0 International (CC BY 4.0)

Submission Number: 1780