Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees
Machine Learning
2023-03-21 v2 Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
Abstract
We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for strongly convex losses. We benchmark against competing protocols and show the empirical superiority of the proposed protocols. Finally, we remark that our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server. The code for evaluation is provided in https://github.com/wanglun1996/secure-robust-federated-learning.
Keywords
Cite
@article{arxiv.2205.11765,
title = {Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees},
author = {Banghua Zhu and Lun Wang and Qi Pang and Shuai Wang and Jiantao Jiao and Dawn Song and Michael I. Jordan},
journal= {arXiv preprint arXiv:2205.11765},
year = {2023}
}