Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions

Rustem Islamov, Grigory Malinovsky, Alexander Gaponov, Aurelien Lucchi, Peter Richtárik et al.|March 24, 2026arXiv

Key Takeaway

You can now build federated learning systems that defend against both Byzantine attacks and privacy breaches simultaneously, without needing unrealistic assumptions like bounded gradients or extra server datasets.

Summary

This paper tackles two critical security issues in federated learning: protecting against malicious servers (Byzantine attacks) and preventing data leakage (differential privacy).

safety training efficiency

Key Terms

federated-learning differential-privacy byzantine-robustness gradient-clipping robust-aggregation