FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System

arXiv:2303.10837v3 Announce Type: replace-cross
Abstract: Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal information by inversion attacks. Privacy-preserving methods, such as homomorphic encryption (HE), then become necessary for FL training. Despite HE's privacy advantages, its applications suffer from impractical overheads, especially for foundation models. In this paper, we present FedML-HE, the first practical federated …

arxiv attacks cs.cr cs.lg data devices distributed encryption federated federated learning homomorphic encryption information local machine machine learning machine learning models may personal personal information privacy privacy concerns reveal sensitive server system trains updates