A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report)
Abstract
Recent research efforts indicate that federated learning (FL) systems are vulnerable to a variety of security breaches. While numerous defense strategies have been suggested, they are mainly designed to counter specific attack patterns and lack adaptability, rendering them less effective when facing uncertain or adaptive threats. This work models adversarial FL as a Bayesian Stackelberg Markov game (BSMG) between the defender and the attacker to address the lack of adaptability to uncertain adaptive attacks. We further devise an effective meta-learning technique to solve for the Stackelberg equilibrium, leading to a resilient and adaptable defense. The experiment results suggest that our meta-Stackelberg learning approach excels in combating intense model poisoning and backdoor attacks of indeterminate types.
Cite
@article{arxiv.2306.13273,
title = {A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report)},
author = {Henger Li and Tianyi Xu and Tao Li and Yunian Pan and Quanyan Zhu and Zizhan Zheng},
journal= {arXiv preprint arXiv:2306.13273},
year = {2025}
}
Comments
This submission is a technical report for "A First Order Meta Stackelberg Method for Robust Federated Learning" (arXiv:2306.13800). We later submitted a full paper, "Meta Stackelberg Game: Robust Federated Learning Against Adaptive and Mixed Poisoning Attacks" (arXiv:2410.17431), which fully incorporates this report in its Appendix. To avoid duplication, we withdraw this submission