Tangent differential privacy

TL;DR

This paper introduces tangent differential privacy, a new privacy framework tailored to specific data distributions, which uses general distribution distances and guarantees privacy through entropic regularization in risk minimization.

Contribution

It proposes tangent differential privacy, a novel privacy concept that adapts to specific data distributions and employs entropic regularization for privacy guarantees.

Findings

Tangent differential privacy is tailored to specific data distributions.

It allows for general distribution distances like total variation and Wasserstein.

Entropic regularization guarantees tangent differential privacy under broad conditions.

Abstract

Differential privacy is a framework for protecting the identity of individual data points in the decision-making process. In this note, we propose a new form of differential privacy called tangent differential privacy. Compared with the usual differential privacy that is defined uniformly across data distributions, tangent differential privacy is tailored towards a specific data distribution of interest. It also allows for general distribution distances such as total variation distance and Wasserstein distance. In the case of risk minimization, we show that entropic regularization guarantees tangent differential privacy under rather general conditions on the risk function.