Privacy-aware Distributed Hypothesis Testing in Gray-Wyner Network with Side Information

TL;DR

This paper investigates privacy-aware distributed hypothesis testing in a Gray-Wyner network with side information, deriving bounds on the trade-offs between testing accuracy and privacy preservation.

Contribution

It introduces an achievable inner bound for the problem, incorporating a non-asymptotic analysis of output statistics and privacy constraints.

Findings

Derived an inner bound for hypothesis testing with privacy constraints.

Analyzed the trade-off between testing performance and privacy preservation.

Utilized non-asymptotic output statistics of random binning.

Abstract

The problem of distributed binary hypothesis testing in the Gray-Wyner network with side information is studied in this paper. An observer has access to a discrete memoryless and stationary source and describes its observation to two detectors via one common and two private channels. The channels are considered error-free but rate-limited. Each detector also has access to its own discrete memoryless and stationary source, i.e., the side information. The goal is to perform two distinct binary hypothesis testings on the joint distribution of observations at detectors. Additionally, the observer aims to keep a correlated latent source private against the detectors. Equivocation is used as the measure of the privacy preserved for the latent source. An achievable inner bound is derived for the general case by introducing a non-asymptotic account of the output statistics of the random binning.