arXiv：cs.LG（机器学习，全量分类）· Seyed Mohammad Azimi-Abarghouyi·· 13 小时前AI 评分34
联邦学习中的渐进分辨率安全聚合（PSA）
Progressive-Resolution Secure Aggregation for Federated Learning
AI 导读
研究者提出渐进分辨率安全聚合（PSA），让客户端只需上传一次，服务器便可在后续经非串通发布控制器授权后，逐层获得同一聚合结果的更精细分辨率，无需客户端重新参与。该方法将每个裁剪、加噪的更新表示为兼容的嵌套格数字，各可独立发布的层由安全聚合和一个服务器无法获取的聚合填充保护。
正文
Abstract:Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the aggregate precision when clients upload. We introduce and formulate a new progressive-resolution secure-aggregation functionality in which clients upload once and successively finer resolutions of the same aggregate can later be authorized without renewed client participation. To realize this functionality, we propose progressive-resolution secure aggregation (PSA): each clipped, dithered update is represented by compatible nested-lattice digits; separately releasable layers are protected by secure aggregation and an additional aggregate pad that remains unavailable to the server until a non-colluding release controller authorizes that layer.
| Subjects: | Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC); Information Theory (cs.IT); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00695 [cs.CR] |
| (or arXiv:2610.00695v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00695 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Seyed Mohammad Azimi-Abarghouyi [view email]
[v1]
Wed, 30 Sep 2026 20:38:11 UTC (91 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org