Information - theoretic approaches to differential privacy

Unsal, Ayse ; Önen, Melek
Submitted to ArXiV, 22 March 2022

This tutorial studies relationships between differential privacy and various information-theoretic measures using several selective articles. In particular, we present how these relationships can provide new interpretations for the privacy guarantee in systems that deploy differential privacy in an information-theoretic framework. To this end, this work offers an extensive summary on the existing literature that makes use of information- theoretic measures and tools such as mutual information, min entropy, Kullback-Leibler divergence and rate-distortion function for quantifying differential privacy in various settings.


Type:
Report
Date:
2022-03-22
Department:
Digital Security
Eurecom Ref:
6697
Copyright:
© EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Submitted to ArXiV, 22 March 2022 and is available at :

PERMALINK : https://www.eurecom.fr/publication/6697