arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.04249cs.DS
收藏

通用对称范数估计的私有数据流分析

Private Data Stream Analysis for Universal Symmetric Norm Estimation

Vladimir Braverman, Joel Manning, Zhiwei Steven Wu, Samson Zhou

AI总结:

本文针对差分隐私约束下的数据流对称范数估计问题,提出一个通用可参数化框架,通过按坐标幅值分层并发布充分统计量,实现任意数量对称范数的同时近似且无额外隐私损失,并支持亚线性空间实现。

摘要:

我们研究如何在差分隐私约束下发布数据流的汇总统计信息。具体而言,我们专注于发布对称范数族,这类范数在输入数据流上对符号翻转和逐坐标置换保持不变,并包含 $L_p$ 范数、$k$-support 范数、top-$k$ 范数以及 box 范数作为特例。尽管可以为每个对称范数分别设计和分析一个机制,但我们提出了一个通用的可参数化框架,该框架以差分隐私方式发布若干充分统计量,从而可以同时计算所有对称范数的近似值。我们的框架根据底层频率向量各坐标的幅值将其划分为不同层级,对重要层级中的“重”坐标发布近似频率,并对重要层级中的“轻”坐标发布近似层级大小。令人惊讶的是,我们的机制允许发布任意数量的对称范数近似值,而不会产生任何额外开销或额外的隐私损失。此外,我们的机制允许对每个对称范数实现 $(1+α)$-近似,并且在精度和隐私参数的许多取值范围内,可以在流模型中使用亚线性空间实现。

英文摘要:

We study how to release summary statistics on a data stream subject to the constraint of differential privacy. In particular, we focus on releasing the family of symmetric norms, which are invariant under sign-flips and coordinate-wise permutations on an input data stream and include $L_p$ norms, $k$-support norms, top-$k$ norms, and the box norm as special cases. Although it may be possible to design and analyze a separate mechanism for each symmetric norm, we propose a general parametrizable framework that differentially privately releases a number of sufficient statistics from which the approximation of all symmetric norms can be simultaneously computed. Our framework partitions the coordinates of the underlying frequency vector into different levels based on their magnitude and releases approximate frequencies for the "heavy" coordinates in important levels and releases approximate level sizes for the "light" coordinates in important levels. Surprisingly, our mechanism allows for the release of an arbitrary number of symmetric norm approximations without any overhead or additional loss in privacy. Moreover, our mechanism permits $(1+α)$-approximation to each of the symmetric norms and can be implemented using sublinear space in the streaming model for many regimes of the accuracy and privacy parameters.

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。

↑