Dropout is NOT All You Need to Prevent Gradient Leakage. (arXiv:2208.06163v2 [cs.LG] UPDATED)

Gradient inversion attacks on federated learning systems reconstruct client
training data from exchanged gradient information. To defend against such
attacks, a variety of defense mechanisms were proposed. However, they usually
lead to an unacceptable trade-off between privacy and model utility. Recent
observations suggest that dropout could mitigate gradient leakage and improve
model utility if added to neural networks. Unfortunately, this phenomenon has
not been systematically researched yet. In this work, we thoroughly analyze the
effect of dropout on iterative gradient …