English(EN) Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization

揭示新的联邦学习安全聚合方案

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了一种新的联邦学习信息论安全聚合方案，该方案可适应异构客户端量化级别。该协议通过防止泄露单个模型更新来解决现有方法中的隐私泄露问题，即使在客户端掉线和串通的情况下也是如此。该方案利用阈值秘密共享结构，尽管客户端使用不同的量化组，但仍可从相同的线性整数系统中生成秘密共享。 AI

影响增强了联邦学习的隐私性，可能实现更安全的协作模型训练。

排序理由学术论文，详细介绍了特定研究领域的新技术方法。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了特定研究领域的新技术方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Shreya Meel, Sennur Ulukus, Itzhak Tamo · 2026-10-28 04:00

具有异构客户端量化的信息论安全聚合

arXiv:2610.35833v1 Announce Type: cross Abstract: 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…