A Design Framework for Strongly $\chi^2$-Private Data Disclosure
Abstract
In this paper, we study a stochastic disclosure control problem using information-theoretic methods. The useful data to be disclosed depend on private data that should be protected. Thus, we design a privacy mechanism to produce new data which maximizes the disclosed information about the useful data under a strong -privacy criterion. For sufficiently small leakage, the privacy mechanism design problem can be geometrically studied in the space of probability distributions by a local approximation of the mutual information. By using methods from Euclidean information geometry, the original highly challenging optimization problem can be reduced to a problem of finding the principal right-singular vector of a matrix, which characterizes the optimal privacy mechanism. In two extensions we first consider a scenario where an adversary receives a noisy version of the user's message and then we look for a mechanism which finds based on observing , maximizing the mutual information between and while satisfying the privacy criterion on and under the Markov chain .
Cite
@article{arxiv.2009.01704,
title = {A Design Framework for Strongly $\chi^2$-Private Data Disclosure},
author = {Amirreza Zamani and Tobias J. Oechtering and Mikael Skoglund},
journal= {arXiv preprint arXiv:2009.01704},
year = {2021}
}
Comments
16 pages, 2 figures