arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07134stat.MLcs.CRcs.LG
收藏

基于FFT的离散值机制和下采样高斯机制的紧差分保密

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Helsinki Institute for Information Technology HIIT(赫尔辛基信息技术研究所HIIT);University of Helsinki(赫尔辛基大学);Aalto University(阿尔托大学)

Antti Koskela, Joonas Jälkö, Lukas Prediger, Antti Honkela

摘要:

我们提出了一个数值会计评估紧$(\varepsilon,δ)$隐私损失的算法与离散一维输出。该方法是基于隐私损失分布形式主义,它使用了最近推出的快速傅立叶变换为基础的会计技术。我们进行了误差分析的隐私损失分布,导致严格的下限和上限的真实$(\varepsilon,δ)$值的时刻界的方法。作为一个应用,我们提出了一种新的方法来准确的隐私会计的子采样高斯机制。这完成了先前提出的分析,给出严格的下限和上限的隐私参数。我们证明了性能的会计二项式机制,并表明,我们的方法允许降低噪声方差高达75%,在同等的隐私文献中现有的界限相比。我们还说明了如何计算紧边界的指数机制应用于计数查询。

英文摘要:

We propose a numerical accountant for evaluating the tight $(\varepsilon,δ)$-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it uses the recently introduced fast Fourier transform based accounting technique. We carry out an error analysis of the method in terms of moment bounds of the privacy loss distribution which leads to rigorous lower and upper bounds for the true $(\varepsilon,δ)$-values. As an application, we present a novel approach to accurate privacy accounting of the subsampled Gaussian mechanism. This completes the previously proposed analysis by giving strict lower and upper bounds for the privacy parameters. We demonstrate the performance of the accountant on the binomial mechanism and show that our approach allows decreasing noise variance up to 75 percent at equal privacy compared to existing bounds in the literature. We also illustrate how to compute tight bounds for the exponential mechanism applied to counting queries.

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。

↑