SVFL: Efficient Secure Aggregation and Verification for Cross-Silo
Federated Learning
Abstract
Cross-silo federated learning (FL) allows organizations to
collaboratively train machine learning (ML) models by sending their
local gradients to a server for aggregation, without having to disclose
their data. This paper proposes SVFL, an efficient protocol for
cross-silo FL, that supports both secure gradient aggregation and
verification. We evaluate the performance of SVFL and show, by
complexity analysis and experimental evaluations, that its computation
and communication overhead remain low even on large datasets, with a
negligible accuracy loss (less than $1\%$).
Furthermore, we conduct an experimental comparison between SVFL and
other existing FL protocols, and show that SVFL achieves significant
efficiency improvements in both computation and communication.