arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.04591cs.CRcs.DScs.LGstat.ML
收藏

通过混洗实现更强的Rényi差分隐私与近似差分隐私放大

Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy

Apple(苹果公司)

Vitaly Feldman, Audra McMillan, Kunal Talwar

AI总结:

本文从理论和数值两方面改进了混洗模型的隐私放大结果,首次给出LDP随机化器混洗输出的Rényi差分隐私参数的渐近最优分析,并提出新分析方法在所有参数设置下获得更紧的数值界。

摘要:

差分隐私的混洗模型作为一种介于标准本地模型与中心模型之间的中间信任模型,已引起广泛关注[EFMRTT19; CSUZZ19]。该模型中的一个关键结果是,对本地随机化的数据进行随机混洗会放大差分隐私保证。这种放大意味着对于数据以匿名方式贡献的系统而言,能够提供显著更强的隐私保证[BEMMRLRKTS17]。在本文中,我们从理论和数值两方面改进了当前最先进的混洗隐私放大结果。我们的第一个贡献是对LDP随机化器混洗输出的Rényi差分隐私参数进行了首个渐近最优分析。我们的第二个贡献是一种新的混洗隐私放大分析方法。该分析改进了[FMT20]中的技术,并在所有参数设置下都得到了更紧的数值界。

英文摘要:

The shuffle model of differential privacy has gained significant interest as an intermediate trust model between the standard local and central models [EFMRTT19; CSUZZ19]. A key result in this model is that randomly shuffling locally randomized data amplifies differential privacy guarantees. Such amplification implies substantially stronger privacy guarantees for systems in which data is contributed anonymously [BEMMRLRKTS17]. In this work, we improve the state of the art privacy amplification by shuffling results both theoretically and numerically. Our first contribution is the first asymptotically optimal analysis of the Rényi differential privacy parameters for the shuffled outputs of LDP randomizers. Our second contribution is a new analysis of privacy amplification by shuffling. This analysis improves on the techniques of [FMT20] and leads to tighter numerical bounds in all parameter settings.

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。

↑