arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07656cs.ITmath.IT
收藏

联邦子模型学习中的信息论隐私

Information-Theoretic Privacy in Federated Submodel learning

Minchul Kim, Jungwoo Lee

摘要:

我们考虑联邦子模型学习中的信息论隐私,其中全局服务器具有多个子模型。与传统联邦子模型学习中采用安全聚合来保证隐私的隐私性相比,信息论隐私性对本地机器的子模型选择提供了更强的保护。我们提出了一个可实现的计划,部分采用传统的私人信息检索(PIR)计划,实现最小的下载量。关于计算和通信开销,我们比较了可实现的计划与一个天真的方法,联邦子模型学习与信息理论的隐私。

英文摘要:

We consider information-theoretic privacy in federated submodel learning, where a global server has multiple submodels. Compared to the privacy considered in the conventional federated submodel learning where secure aggregation is adopted for ensuring privacy, information-theoretic privacy provides the stronger protection on submodel selection by the local machine. We propose an achievable scheme that partially adopts the conventional private information retrieval (PIR) scheme that achieves the minimum amount of download. With respect to computation and communication overhead, we compare the achievable scheme with a naive approach for federated submodel learning with information-theoretic privacy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑