DDP-SA combines client-side Laplace noise perturbation with full-threshold additive secret sharing to let federated learning servers reconstruct only aggregated noisy gradients without exposing individual client updates.
Differentially private federated learning with local regularization and sparsification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DDP-SA: Scalable Privacy-Preserving Federated Learning via Distributed Differential Privacy and Secure Aggregation
DDP-SA combines client-side Laplace noise perturbation with full-threshold additive secret sharing to let federated learning servers reconstruct only aggregated noisy gradients without exposing individual client updates.