Dropout against Deep Leakage from Gradients. (arXiv:2108.11106v2 [cs.LG] UPDATED)

As the scale and size of the data increases significantly nowadays, federal
learning (Bonawitz et al. [2019]) for high performance computing and machine
learning has been much more important than ever before (Abadi et al. [2016]).
People used to believe that sharing gradients seems to be safe to conceal the
local training data during the training stage. However, Zhu et al. [2019]
demonstrated that it was possible to recover raw data from the model training
data by detecting gradients. They …

arxiv dropout