arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.08367cs.CRcs.CYcs.LG
收藏

使用分布隐私机制保护数据集的全局属性

Protecting Global Properties of Datasets with Distribution Privacy Mechanisms

The University of Melbourne(墨尔本大学)

Michelle Chen, Olga Ohrimenko

AI总结:

本研究针对数据集全局属性的机密性问题,提出基于分布隐私框架,扩展Wasserstein机制和Gaussian机制,有效抵御属性推断攻击,并在隐私与效用间取得更优平衡。

摘要:

我们考虑确保在数据集的多条记录上聚合的数据集属性的机密性问题。这些属性可以编码敏感信息,如商业机密或人口统计数据,同时涉及的数据保护概念与文献中通常讨论的单个记录隐私不同。在本研究中,我们展示了如何应用分布隐私框架来形式化此类数据机密性。我们将 Pufferfish 隐私的 Wasserstein 机制和属性隐私的 Gaussian 机制扩展到该框架中,然后分析了它们的基础数据假设以及如何放宽这些假设。随后,我们实证评估了这些机制的隐私-效用权衡,并将其应用于针对数据集全局属性的实际属性推断攻击。结果表明,我们的机制确实能够降低攻击的有效性,同时提供的效用显著优于粗糙的组差分隐私基线。因此,我们的工作为保护数据集全局属性的理论机制及其实践评估奠定了基础。

英文摘要:

We consider the problem of ensuring confidentiality of dataset properties aggregated over many records of a dataset. Such properties can encode sensitive information, such as trade secrets or demographic data, while involving a notion of data protection different to the privacy of individual records typically discussed in the literature. In this work, we demonstrate how a distribution privacy framework can be applied to formalize such data confidentiality. We extend the Wasserstein Mechanism from Pufferfish privacy and the Gaussian Mechanism from attribute privacy to this framework, then analyze their underlying data assumptions and how they can be relaxed. We then empirically evaluate the privacy-utility tradeoffs of these mechanisms and apply them against a practical property inference attack which targets global properties of datasets. The results show that our mechanisms can indeed reduce the effectiveness of the attack while providing utility substantially greater than a crude group differential privacy baseline. Our work thus provides groundwork for theoretical mechanisms for protecting global properties of datasets along with their evaluation in practice.

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。

↑