Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees. (arXiv:2205.11765v2 [cs.LG] UPDATED)

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.