A Secure Aggregation Scheme Based on Additive Secret Sharing for Federated Learning
To address privacy leakage in centralized aggregation, this paper proposes FedShare, a multi-server secure aggregation scheme based on additive secret sharing. It adopts a three-layer architecture (clients, ordinary aggregation servers, and a super aggregation server), where client model updates are split into secret shares and securely aggregated across servers so that no single server can access complete model parameters. To handle client data imbalance, a data-size-based weighting mechanism is applied before secret sharing to ensure consistency with FedAvg, and finite-field operations with quantization recovery are used to bound quantization errors under integer arithmetic. Experiments on MNIST and CIFAR-10 show that FedShare preserves model accuracy comparable to FedAvg while providing privacy protection, with only 7.83% and 17.21% increases in average per-round training time, demonstrating a good trade-off among privacy, utility, and efficiency.