用少量客户端聚合器实现高效安全联邦学习，速度提升4.6倍。
DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
- 引入客户端聚合器小组，本地计算部分和后返回共享值。
- 处理10万维更新向量时比OPA快4.6倍，通信与计算开销更低。
- 适合大规模5G联邦学习场景，抗服务器窥探与有限合谋攻击。
联邦学习允许分布式客户端协作训练模型，但原始方法会使客户端更新暴露于中心服务器。安全聚合方案可保护隐私免受诚实但好奇的服务器侵害，但现有方法常面临多轮通信、重公钥操作或难以应对客户端掉线问题。近期方法如一次性私有聚合（OPA）将每轮迭代的通信降至单次交互，但对服务器和客户端均带来巨大密码学与计算开销。本文提出新协议DisAgg，利用一组小型客户端聚合器执行聚合：每个客户端将其更新向量秘密分享给聚合器，聚合器本地计算部分和，并仅返回聚合后的共享值供服务器重建。该设计消除了本地掩码和昂贵的同态加密，降低端点计算量的同时，仍能抵御好奇服务器及有限合谋客户端的威胁。通过在通信与计算成本间实现最优权衡，DisAgg可在100,000个5G客户端上处理100,000维更新向量，相比此前最佳方案OPA实现4.6倍加速。
原文摘要 · Abstract (English)
Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect privacy against an honest-but-curious server, but existing approaches often suffer from many communication rounds, heavy public-key operations, or difficulty handling client dropouts. Recent methods like One-Shot Private Aggregation (OPA) cut rounds to a single server interaction per FL iteration, yet they impose substantial cryptographic and computational overhead on both server and clients. We propose a new protocol called DisAgg that leverages a small committee of clients called Aggregators to perform the aggregation itself: each client secret-shares its update vector to Aggregators, which locally compute partial sums and return only aggregated shares for server-side reconstruction. This design eliminates local masking and expensive homomorphic encryption, reducing endpoint computation while preserving privacy against a curious server and a limited fraction of colluding clients. By leveraging optimal trade-offs between communication and computation costs, DisAgg processes 100k-dimensional update vectors from 100k 5G clients with a 4.6x speedup compared to OPA, the previous best protocol.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。