arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.13239cs.CR
收藏

不确定性原则是隐私保护微数据的代价

An Uncertainty Principle is a Price of Privacy-Preserving Microdata

John Abowd, Robert Ashmead, Ryan Cumings-Menon, Simson Garfinkel, Daniel Kifer, Philip Leclerc, William Sexton, Ashley Simpson, Christine Task, Pavel Zhuravlev

摘要:

受隐私保护的微数据通常是差分隐私算法的期望输出,因为微数据对于下游用户来说是熟悉和方便的。然而,这种便利是有统计代价的。我们表明,一个不确定性的原则管理的利益(“总和查询”)与准确性的人口之间的权衡,其组成部分的子群体(“点查询”)。与不需要产生微数据的差分私有查询应答系统相比,准确性可以降低对数因子。例如,在纯差分隐私的情况下,在没有微数据要求的情况下,可以向和查询和所有点查询提供噪声答案,同时保证每个答案具有平方误差$O(1/ε^2)$。对于微数据需求,必须在允许某些点查询的额外$\log^2(d)$因子($d$是点查询的数量)或允许求和查询的额外$O(d^2)$因子之间进行选择。我们提出了纯,近似和集中的差分隐私的下限。我们提出了缓解策略,并创建了一个基准数据集的集合,可用于公众研究这个问题。

英文摘要:

Privacy-protected microdata are often the desired output of a differentially private algorithm since microdata is familiar and convenient for downstream users. However, there is a statistical price for this kind of convenience. We show that an uncertainty principle governs the trade-off between accuracy for a population of interest ("sum query") vs. accuracy for its component sub-populations ("point queries"). Compared to differentially private query answering systems that are not required to produce microdata, accuracy can degrade by a logarithmic factor. For example, in the case of pure differential privacy, without the microdata requirement, one can provide noisy answers to the sum query and all point queries while guaranteeing that each answer has squared error $O(1/ε^2)$. With the microdata requirement, one must choose between allowing an additional $\log^2(d)$ factor ($d$ is the number of point queries) for some point queries or allowing an extra $O(d^2)$ factor for the sum query. We present lower bounds for pure, approximate, and concentrated differential privacy. We propose mitigation strategies and create a collection of benchmark datasets that can be used for public study of this problem.

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。

↑