Privacy Against Brute-Force Inference Attacks

Osia, Seyed Ali; Rassouli, Borzoo; Haddadi, Hamed; Rabiee, Hamid R.; Gündüz, Deniz

doi:10.48550/arxiv.1902.00329

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, privacy and utility objectives compete with each other, making the design of privacy mechanisms a non-trivial task. When data privacy and statistical utility are measured using information-theoretic quantities (e.g., mutual information), most methods for the analysis and design of privacy mechanisms rely on the implicit assumption that the data distribution is, for the most part, known [10,14,[18][19][20][21][22][23][24][25]. In practice, the designer has access only to a sample from the true distribution.…”

Section: Introductionmentioning

confidence: 99%

On the Robustness of Information-Theoretic Privacy Measures and Mechanisms

Díaz

Wang

Calmon

et al. 2020

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

Consider a data publishing setting for a dataset composed by both private and non-private features. The publisher uses an empirical distribution, estimated from n i.i.d. samples, to design a privacy mechanism which is applied to new fresh samples afterward. In this paper, we study the discrepancy between the privacy-utility guarantees for the empirical distribution, used to design the privacy mechanism, and those for the true distribution, experienced by the privacy mechanism in practice. We first show that, for any privacy mechanism, these discrepancies vanish at speed O(1/ √ n) with high probability. These bounds follow from our main technical results regarding the Lipschitz continuity of the considered information leakage measures. Then we prove that the optimal privacy mechanisms for the empirical distribution approach the corresponding mechanisms for the true distribution as the sample size n increases, thereby establishing the statistical consistency of the optimal privacy mechanisms. Finally, we introduce and study uniform privacy mechanisms which, by construction, provide privacy to all the distributions within a neighborhood of the estimated distribution and, thereby, guarantee privacy for the true distribution with high probability.

show abstract