arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.13697cs.CR
收藏

论差分隐私构成中数据库的选择

On the Choice of Databases in Differential Privacy Composition

Valentin Hartmann, Vincent Bindschaedler, Robert West

摘要:

差分隐私(DP)是一种广泛应用的在维护用户隐私的同时发布数据的范例。它的成功在很大程度上归功于其组合属性,即使在多个数据发布的情况下也能保证隐私。因此,合成得到了很多关注,从研究界:有几个合成定理的对手与不同数量的灵活性,在他们的选择机制。但是除了机制之外,对手还可以选择调用这些机制的数据库。分析DP机制组成的经典工具,即所谓的组合实验,既不允许对数据库进行约束,也不允许对手对数据库成员的先验知识进行不同的假设。因此,我们提出了一个广义组合实验(GCE),它具有这种灵活性。我们发现,组成定理,持有相对于经典的组成实验也持有相对于最坏的情况下的GCE。这意味着,现有的组合定理提供了更多的情况下,比明确涵盖的经典组合实验的隐私保证。除了这些理论的见解,我们展示了两个实际应用的GCE:第一个应用程序是给更好的隐私边界的存在下,对数据库的选择的限制;第二个应用程序是原因对手的先验知识如何影响隐私泄漏。在这种情况下,我们展示了一个没有信息的先验和二次抽样,DP中的一个重要原语的对手之间的连接。据我们所知,本文是第一次分析数据库之间的相互作用,在DP组合,从而得到更好的理解组合和实用的工具,以获得更好的组合界限。

英文摘要:

Differential privacy (DP) is a widely applied paradigm for releasing data while maintaining user privacy. Its success is to a large part due to its composition property that guarantees privacy even in the case of multiple data releases. Consequently, composition has received a lot of attention from the research community: there exist several composition theorems for adversaries with different amounts of flexibility in their choice of mechanisms. But apart from mechanisms, the adversary can also choose the databases on which these mechanisms are invoked. The classic tool for analyzing the composition of DP mechanisms, the so-called composition experiment, neither allows for incorporating constraints on databases nor for different assumptions on the adversary's prior knowledge about database membership. We therefore propose a generalized composition experiment (GCE), which has this flexibility. We show that composition theorems that hold with respect to the classic composition experiment also hold with respect to the worst case of the GCE. This implies that existing composition theorems give a privacy guarantee for more cases than are explicitly covered by the classic composition experiment. Beyond these theoretical insights, we demonstrate two practical applications of the GCE: the first application is to give better privacy bounds in the presence of restrictions on the choice of databases; the second application is to reason about how the adversary's prior knowledge influences the privacy leakage. In this context, we show a connection between adversaries with an uninformative prior and subsampling, an important primitive in DP. To the best of our knowledge, this paper is the first to analyze the interplay between the databases in DP composition, and thereby gives both a better understanding of composition and practical tools for obtaining better composition bounds.

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。

↑