Fluent: Round-efficient Secure Aggregation for Private Federated Learning

arXiv:2403.06143v1 Announce Type: new
Abstract: Federated learning (FL) facilitates collaborative training of machine learning models among a large number of clients while safeguarding the privacy of their local datasets. However, FL remains susceptible to vulnerabilities such as privacy inference and inversion attacks. Single-server secure aggregation schemes were proposed to address these threats. Nonetheless, they encounter practical constraints due to their round and communication complexities. This work introduces Fluent, a round and communication-efficient secure aggregation scheme for private FL. Fluent has …

address aggregation arxiv attacks clients cs.ai cs.cr datasets federated federated learning large local machine machine learning machine learning models privacy private server single threats training vulnerabilities