arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.18157cs.CRcs.DB
收藏

具有个性化隐私的 Shuffle 模型的增强隐私界

Enhanced Privacy Bound for Shuffle Model with Personalized Privacy

Yixuan Liu, Yuhan Liu, Li Xiong, Yujie Gu, Hong Chen

AI总结:

针对shuffle模型在个性化本地隐私设置下隐私界不紧致的问题,通过假设检验精确推导克隆生成概率,并在$f$-DP框架下利用分布凸性分析不可区分性,提出一般且更紧致的隐私界,显著优于现有结果。

摘要:

差分隐私(DP)的 shuffle 模型是一种增强型隐私协议,它在本地用户和中央数据管理者之间引入了一个中间可信服务器。它通过匿名化和打乱本地随机化数据,显著增强了中央 DP 保证。然而,由于其复杂的随机化协议,推导出紧致的隐私界具有挑战性。虽然现有大多数工作集中在统一的本地隐私设置上,但本工作专注于为每个用户需要个性化本地隐私的更实际设置推导中央隐私界。为了界定 shuffle 后的隐私,我们首先需要捕获每个用户生成相邻数据点克隆的概率。其次,我们需要量化相邻数据集上克隆数量两种分布之间的不可区分性。现有工作要么不准确捕获概率,要么低估相邻数据集之间的不可区分性。受此启发,我们开发了一种更精确的分析方法,为任意 DP 机制产生了一般且更紧致的界。首先,我们通过假设检验推导克隆生成概率,这导致了对该概率更准确的刻画。其次,我们在 $f$-DP 语境下分析不可区分性,利用分布的凸性来实现更紧致的隐私界。理论和数值结果证明,我们的界显著优于文献中现有结果。

英文摘要:

The shuffle model of Differential Privacy (DP) is an enhanced privacy protocol which introduces an intermediate trusted server between local users and a central data curator. It significantly amplifies the central DP guarantee by anonymizing and shuffling the local randomized data. Yet, deriving a tight privacy bound is challenging due to its complicated randomization protocol. While most existing work are focused on unified local privacy settings, this work focuses on deriving the central privacy bound for a more practical setting where personalized local privacy is required by each user. To bound the privacy after shuffling, we first need to capture the probability of each user generating clones of the neighboring data points. Second, we need to quantify the indistinguishability between two distributions of the number of clones on neighboring datasets. Existing works either inaccurately capture the probability, or underestimate the indistinguishability between neighboring datasets. Motivated by this, we develop a more precise analysis, which yields a general and tighter bound for arbitrary DP mechanisms. Firstly, we derive the clone-generating probability by hypothesis testing %from a randomizer-specific perspective, which leads to a more accurate characterization of the probability. Secondly, we analyze the indistinguishability in the context of $f$-DP, where the convexity of the distributions is leveraged to achieve a tighter privacy bound. Theoretical and numerical results demonstrate that our bound remarkably outperforms the existing results in the literature.

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。

↑