FSSA: Fast secure single-server aggregation with optimal communication rounds

Federated learning (FL) allows a large number of clients to collaboratively train machine learning (ML) models by sending only their local gradients to a central server for aggregation in each training iteration, without sending their raw training data. Unfortunately, recent attacks on FL demonstrate that local gradients may leak information about local training data. In response to such attacks, Bonawitz et al. (CCS 2017) proposed a secure aggregation protocol that allows a server to compute the sum of clients’ local gradients securely. However, their secure aggregation protocol requires at least 4 rounds of communication between each client and the server in each training iteration. The number of communication rounds is closely related not only to the total communication cost but also to the ML model accuracy, as the number of communication rounds affects client dropouts. In this paper, we propose FSSA, a 3-round secure aggregation protocol, that is efficient in terms of computation and communication, and resilient to client dropouts. We prove the security of FSSA in the honest-but-curious setting and demonstrate that the security can be maintained even if an arbitrarily chosen subset of clients drops out at any time. We evaluate the performance of FSSA and show that its computation and communication overhead remain low even on large datasets. Furthermore, we conduct an experimental comparison between FSSA and the protocol by Bonawitz et al. The comparison results show that, in addition to reducing the number of communication rounds, FSSA achieves a significant improvement in computational efficiency.