byzantine-robustness

Tag

Cards List
#byzantine-robustness

Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness

arXiv cs.LG · 2026-07-03 Cached

This paper reveals a non-monotonic effect of privacy on generalization error in Byzantine-robust distributed learning: in high-noise (strong privacy) regimes, increasing privacy reduces generalization error, while in low-noise (weaker privacy) regimes, increasing privacy degrades generalization.

0 favorites 0 likes
#byzantine-robustness

Power to the Clients: Federated Learning in a Dictatorship Setting

arXiv cs.CL · 2026-04-20 Cached

This paper introduces 'dictator clients'—a novel class of malicious participants in federated learning capable of erasing other clients' contributions while preserving their own—and provides theoretical analysis of their impact on model convergence, including scenarios with multiple adversarial clients.

0 favorites 0 likes
← Back to home

Submit Feedback