On the Contractivity of Privacy Mechanisms

TL;DR

This paper introduces a new method to compare privacy mechanisms using the Dobrushin coefficient, linking it to maximal leakage and local differential privacy, and applies it to derive bounds on distribution estimation risks.

Contribution

It provides bounds on the Dobrushin coefficient for privacy mechanisms and applies these to analyze the statistical cost in distribution estimation under privacy constraints.

Findings

Bounds on the Dobrushin coefficient in terms of privacy guarantees

New $ ext{L}_2$-minimax risk bounds under maximal leakage

Quantitative comparison with local differential privacy risk

Abstract

We present a novel way to compare the statistical cost of privacy mechanisms using their Dobrushin coefficient. Specifically, we provide upper and lower bounds for the Dobrushin coefficient of a privacy mechanism in terms of its maximal leakage and local differential privacy guarantees. Given the geometric nature of the Dobrushin coefficient, this approach provides some insights into the general statistical cost of these privacy guarantees. We highlight the strength of this method by applying our results to develop new bounds on the $\ell_2$-minimax risk in a distribution estimation setting under maximal leakage constraints. Specifically, we find its order with respect to the sample size and privacy level, allowing a quantitative comparison with the corresponding local differential privacy $\ell_2$-minimax risk.