English

A Design Framework for Strongly $\chi^2$-Private Data Disclosure

Information Theory 2021-03-24 v2 math.IT

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 χ2\chi^2-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 UU based on observing XX, maximizing the mutual information between UU and YY while satisfying the privacy criterion on UU and ZZ under the Markov chain (Z,Y)XU(Z,Y)-X-U.

Keywords

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

R2 v1 2026-06-23T18:17:46.235Z