Oleksandr Lytvyn

Local versus central differential privacy under final-model privacy attacks in low-client-count cross-silo federated learning

Federated learning reduces the need to centralize raw data, but does not prevent privacy leakage from client updates, aggregation messages, or the final released model. This work compares local differential privacy (LDP), central differential privacy (CDP), record-level differentially private stochastic gradient descen...