Local Differential Privacy for Federated Learning. (arXiv:2202.06053v2 [cs.CR] UPDATED)

Advanced adversarial attacks such as membership inference and model
memorization can make federated learning (FL) vulnerable and potentially leak
sensitive private data. Local differentially private (LDP) approaches are
gaining more popularity due to stronger privacy notions and native support for
data distribution compared to other differentially private (DP) solutions.
However, DP approaches assume that the FL server (that aggregates the models)
is honest (run the FL protocol honestly) or semi-honest (run the FL protocol
honestly while also trying to learn …

differential privacy federated learning local privacy