Kantorovich Mechanism for Pufferfish Privacy

Autor:	Ding, Ni
Rok vydání:	2022
Předmět:	Computer Science - Cryptography and Security Statistics - Applications
Druh dokumentu:	Working Paper
Popis:	Pufferfish privacy achieves $\epsilon$-indistinguishability over a set of secret pairs in the disclosed data. This paper studies how to attain $\epsilon$-pufferfish privacy by exponential mechanism, an additive noise scheme that generalizes the Laplace noise. It is shown that the disclosed data is $\epsilon$-pufferfish private if the noise is calibrated to the sensitivity of the Kantorovich optimal transport plan. Such a plan can be obtained directly from the data statistics conditioned on the secret, the prior knowledge of the system. The sufficient condition is further relaxed to reduce the noise power. It is also proved that the Gaussian mechanism based on the Kantorovich approach attains the $\delta$-approximation of $\epsilon$-pufferfish privacy. Comment: 20 pages, incl. supplementary materials, 4 figures, to appear in proceeding of AISTATS 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2201.07388 Zobrazit plný text záznamu View this record from Arxiv