【论文速递】Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization

英文标题：Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization

arXiv编号：2610.35833
作者：Shreya Meel, Sennur Ulukus, Itzhak Tamo
来源：arXiv
原文链接：https://arxiv.org/abs/2610.35833

中文摘要：
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.

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。