A Survey on Decentralized Federated Learning

no code implementations • 8 Aug 2023 • Edoardo Gabrielli, Giovanni Pica, Gabriele Tolomei

In contrast to standard ML, where data must be collected at the exact location where training is performed, FL takes advantage of the computational capabilities of millions of edge devices to collaboratively train a shared, global model without disclosing their local private data.

Federated Learning Privacy Preserving

Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection

no code implementations • 29 Mar 2023 • Edoardo Gabrielli, Dimitri Belli, Vittorio Miori, Gabriele Tolomei

Current defense mechanisms against model poisoning attacks in federated learning (FL) systems have proven effective up to a certain threshold of malicious clients.

Anomaly Detection Federated Learning +3