Data Leakage in Federated Averaging. (arXiv:2206.12395v3 [cs.LG] UPDATED)

Recent attacks have shown that user data can be recovered from FedSGD
updates, thus breaking privacy. However, these attacks are of limited practical
relevance as federated learning typically uses the FedAvg algorithm. Compared
to FedSGD, recovering data from FedAvg updates is much harder as: (i) the
updates are computed at unobserved intermediate network weights, (ii) a large
number of batches are used, and (iii) labels and network weights vary
simultaneously across client steps. In this work, we propose a new …

arxiv data data leakage