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 2303.17849cs.CRcs.ITmath.IT
收藏

论基于统计的合成数据生成中的 Rényi 差分隐私

On Rényi Differential Privacy in Statistics-Based Synthetic Data Generation

Takayuki Miura, Toshiki Shibahara, Masanobu Kii, Atsunori Ichikawa, Juko Yamamoto, Koji Chida

AI总结:

本文理论评估了利用均值向量和协方差矩阵生成合成数据时的 Rényi 差分隐私,给出了满足该隐私的条件,并在千万级数据规模下验证了其隐私保障。

摘要:

使用合成数据生成进行隐私保护通常利用差分隐私统计量和模型参数来定量表达理论安全性。然而,这些方法未考虑数据生成随机性带来的隐私保护。本文在理论上评估了一种合成数据生成方法中数据生成随机性的 Rényi 差分隐私,该方法使用了原始数据集的均值向量和协方差矩阵。具体而言,对于固定的 $α> 1$,分别在有界邻近条件和无界邻近条件下,展示了使得合成数据生成满足 $(α, ε)$-Rényi 差分隐私的 $ε$ 条件。特别地,在无界条件下,当原始数据集和合成数据集大小为 1000 万时,该机制满足 $(4, 0.576)$-Rényi 差分隐私。还展示了将其转换为传统的 $(ε, δ)$-差分隐私时,该机制满足 $(4.00, 10^{-10})$-差分隐私。

英文摘要:

Privacy protection with synthetic data generation often uses differentially private statistics and model parameters to quantitatively express theoretical security. However, these methods do not take into account privacy protection due to the randomness of data generation. In this paper, we theoretically evaluate Rényi differential privacy of the randomness in data generation of a synthetic data generation method that uses the mean vector and the covariance matrix of an original dataset. Specifically, for a fixed $α> 1$, we show the condition of $\varepsilon$ such that the synthetic data generation satisfies $(α, \varepsilon)$-Rényi differential privacy under a bounded neighboring condition and an unbounded neighboring condition, respectively. In particular, under the unbounded condition, when the size of the original dataset and synthetic datase is 10 million, the mechanism satisfies $(4, 0.576)$-Rényi differential privacy. We also show that when we translate it into the traditional $(\varepsilon, δ)$-differential privacy, the mechanism satisfies $(4.00, 10^{-10})$-differential privacy.

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。

↑