Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees

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.

UniFed: A Benchmark for Federated Learning Frameworks

“…Note that, UniFed focus on features that are commonly supported by the frameworks off the shelf. There are also latest research projects developing more functionalities for better training optimization, better robustness [50], more comprehensive differential privacy, and improved fairness. Most frameworks in our evaluation can potentially be extended for those additional functionalities, which is an interesting future direction.…”