[论文] [论文] Information-Theoretic Secure Aggregation With Heterogeneous Clien...

论文概要

研究领域: ML 作者: Shreya Meel, Sennur Ulukus, Itzhak Tamo 发布时间: 2026-10-26 arXiv: 2610.35833

中文摘要

联邦学习中，安全聚合使服务器能计算 N 个客户端本地模型更新的总和，而不向服务器泄露单个更新的任何信息（总和除外）。不同客户端带宽约束不同，可能选择不同量化级数表示发送的信息。多数安全聚合工作要求客户端把更新参数投影到公共有限群（或域）上，无法直接兼容异构精度约束。现有异构量化安全聚合方法会泄露部分聚合，在特定掉线与客户端-服务器合谋模式下可泄露个体更新片段。为防止这种隐私泄露，我们提出信息论安全聚合方案：容忍客户端掉线、至多 T 个相互合谋并与服务器合谋的半诚实客户端，兼容客户端异构量化。协议采用 (T+1, N) 门限黑盒秘密共享构造——尽管份额因量化不同属于不同代数群，都由同一线性整数方程组生成。

原文摘要

In federated learning (FL), secure aggregation enables a server to compute the sum of local model updates of \(N\) clients, without revealing any information on the individual model updates to the server, beyond their sum. Different clients may be subject to heterogeneous bandwidth constraints, and consequently may choose different numbers of quantization levels to represent the information they send. Most secure aggregation works require the clients to project the values of their update parameters to a common finite group (or field), which does not directly accommodate heterogeneous precision constraints on their transmitted masked updates. Existing approaches of secure aggregation with heterogeneous quantization levels reveal partial aggregates of model-updates, and can reveal segments of individual model updates, under certain dropout and client-server collusion patterns. To prevent this privacy breach, we propose an information-theoretic secure aggregation scheme that tolerates client drop-outs, and up to \(T\) semi-honest clients that collude with each other and with the server, under heterogeneous quantization at clients. Our protocol utilizes the \((T+1, N)\) threshold black-box secret sharing construction, where secret shares of the client updates, despite belonging to distinct algebraic groups owing to different quantization, are generated from identical linear integer systems.

---

*自动采集于 2026-10-28*

#论文 #arXiv #ML #小凯