Local Distribution Obfuscation via Probability Coupling
Local Distribution Obfuscation via Probability Coupling
复制标题
通过概率耦合进行局部分布混淆
DOI：
10.1109/allerton.2019.8919803
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yusuke Kawamoto and Takao Murakami
中科院分区：
文献类型：
--
作者：
青山祐太;大沼祐人;松野裕;松野裕;Yusuke Kawamoto and Takao Murakami
我们引入了一个一般模型的概率扰动的概率分布的局部混淆，例如，通过加入差分私有噪声，并研究其理论特性。具体来说，我们放宽了分布隐私（DistP）的概念，将其推广到分歧，并提出了本地混淆机制，提供分歧分布隐私。为了提供f-发散分布隐私，我们证明了概率扰动噪声应按比例添加到地球移动器的概率分布之间的距离，我们要使难以区分。此外，我们引入了一个本地混淆机制，我们称之为耦合机制，它提供了发散分布隐私，同时通过使用我们要保护的输入分布上的精确/近似辅助信息来优化混淆数据的效用。
We introduce a general model for the local obfuscation of probability distributions by probabilistic perturbation, e.g., by adding differentially private noise, and investigate its theoretical properties. Specifically, we relax a notion of distribution privacy (DistP) by generalizing it to divergence, and propose local obfuscation mechanisms that provide divergence distribution privacy. To provide f-divergence distribution privacy, we prove that probabilistic perturbation noise should be added proportionally to the Earth mover’s distance between the probability distributions that we want to make indistinguishable. Furthermore, we introduce a local obfuscation mechanism, which we call a coupling mechanism, that provides divergence distribution privacy while optimizing the utility of obfuscated data by using exact/approximate auxiliary information on the input distributions we want to protect.