Defense against Privacy Leakage in Federated Learning. (arXiv:2209.05724v1 [cs.LG])

Web: http://arxiv.org/abs/2209.05724

Federated Learning (FL) provides a promising distributed learning paradigm,
since it seeks to protect users privacy by not sharing their private training
data. Recent research has demonstrated, however, that FL is susceptible to
model inversion attacks, which can reconstruct users' private data by
eavesdropping on shared gradients. Existing defense solutions cannot survive
stronger attacks and exhibit a poor trade-off between privacy and performance.
In this paper, we present a straightforward yet effective defense strategy
based on obfuscating the gradients of …

defense federated learning privacy