Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy. (arXiv:2212.04371v1 [cs.LG])

Deep neural networks have strong capabilities of memorizing the underlying
training data, which can be a serious privacy concern. An effective solution to
this problem is to train models with differential privacy, which provides
rigorous privacy guarantees by injecting random noise to the gradients. This
paper focuses on the scenario where sensitive data are distributed among
multiple participants, who jointly train a model through federated learning
(FL), using both secure multiparty computation (MPC) to ensure the
confidentiality of each gradient …

differential privacy federated learning novel privacy