Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy

arXiv:2212.04371v2 Announce Type: replace-cross
Abstract: 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) …

arxiv can capabilities cs.cr cs.lg data differential privacy federated federated learning mechanism networks neural networks noise novel privacy privacy concern problem random serious solution train training training data