LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learning

no code implementations • 26 Jul 2021 • Kamala Varma, Yi Zhou, Nathalie Baracaldo, Ali Anwar

This global model can be corrupted when Byzantine workers send malicious gradients, which necessitates robust methods for aggregating gradients that mitigate the adverse effects of Byzantine inputs.

Federated Learning