Federated learning introduces a novel approach to training machine learning (ML) models on distributed data while preserving user's data privacy. This is done by distributing the model to clients to perform training on their local data and computing the final model at a central server. To prevent any data leakage from the local model updates, various works with focus on secure aggregation for privacy preserving federated learning have been proposed. Despite their merits, most of the existing protocols still incur high communication and computation overhead on the participating entities and might not be optimized to efficiently handle the large update vectors for ML models. In this paper, we present E-seaML, a novel secure aggregation protocol with high communication and computation efficiency. E-seaML only requires one round of communication in the aggregation phase and it is up to 318x and 1224x faster for the user and the server (respectively) as compared to its most efficient counterpart. E-seaML also allows for efficiently verifying the integrity of the final model by allowing the aggregation server to generate a proof of honest aggregation for the participating users. This high efficiency and versatility is achieved by extending (and weakening) the assumption of the existing works on the set of honest parties (i.e., users) to a set of assisting nodes. Therefore, we assume a set of assisting nodes which assist the aggregation server in the aggregation process. We also discuss, given the minimal computation and communication overhead on the assisting nodes, how one could assume a set of rotating users to as assisting nodes in each iteration. We provide the open-sourced implementation of E-seaML for public verifiability and testing.

翻译：联邦学习提出了一种在分布式数据上训练机器学习模型的同时保护用户数据隐私的新方法。该方法通过向客户端分发模型以在本地数据上进行训练，并在中央服务器处计算最终模型。为防止本地模型更新导致数据泄露，已有多种专注于隐私保护联邦学习中安全聚合的研究被提出。尽管这些协议具有优势，但多数现有协议仍会给参与实体带来较高的通信和计算开销，且可能无法高效处理机器学习模型的大规模更新向量。本文提出E-seaML，一种具备高通信与计算效率的新型安全聚合协议。该协议在聚合阶段仅需一轮通信，与最高效的同类协议相比，用户端和服务器端的速度分别提升高达318倍和1224倍。E-seaML还允许聚合服务器为参与用户生成诚实聚合证明，从而高效验证最终模型的完整性。这种高效性与多功能性是通过扩展（并弱化）现有工作中关于诚实参与方（即用户）集的假设，转而引入辅助节点集实现的。因此，我们假设存在一组辅助节点协助聚合服务器完成聚合过程。鉴于辅助节点上的最小计算与通信开销，我们还讨论了每轮迭代中如何将一组轮换用户视为辅助节点。我们开源了E-seaML的实现供公开验证与测试。