On the 'Semantics' of Differential Privacy: A Bayesian Formulation
On the 'Semantics' of Differential Privacy: A Bayesian Formulation
复制标题
关于差异隐私的“语义”：贝叶斯公式
DOI：
10.29012/jpc.v6i1.634
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Adam D. Smith
中科院分区：
文献类型：
--
作者：
S. Kasiviswanathan;Adam D. Smith
差异隐私是对分析和发布统计数据库信息的算法的“隐私”的定义。人们经常声称，差分隐私提供了针对具有任意边信息的对手的保证。在本文中，我们提供了一个精确的配方，这些保证的贝叶斯对手所得出的推论。我们表明，这种提法是满意的“香草”差分隐私以及放松称为（δ，δ）差分隐私。我们的公式遵循最初由Dwork和McSherry [Dwork 2006]提出的思想。据我们所知，本文是第一个明确出现这种提法的地方。放松的定义的分析是新的，本文，并提供了一些具体的指导设置参数时，使用（Δ，Δ）-差分隐私。
Differential privacy is a definition of "privacy'" for algorithms that analyze and publish information about statistical databases. It is often claimed that differential privacy provides guarantees against adversaries with arbitrary side information. In this paper, we provide a precise formulation of these guarantees in terms of the inferences drawn by a Bayesian adversary. We show that this formulation is satisfied by both "vanilla" differential privacy as well as a relaxation known as (epsilon,delta)-differential privacy. Our formulation follows the ideas originally due to Dwork and McSherry [Dwork 2006]. This paper is, to our knowledge, the first place such a formulation appears explicitly. The analysis of the relaxed definition is new to this paper, and provides some concrete guidance for setting parameters when using (epsilon,delta)-differential privacy.