Pufferfish Privacy: An Information-Theoretic Study

TL;DR

This paper introduces an information-theoretic formulation of Pufferfish privacy, called mutual information PP, analyzing its properties, noise mechanisms, and applications in privacy auditing, inference, and stability.

Contribution

It formalizes Pufferfish privacy using mutual information, establishes key properties, and derives noise mechanisms with improved performance under relaxed assumptions.

Findings

Mutual information PP (MI PP) is implied by regular PP.

Convexity, composability, and post-processing properties are established for MI PP.

Derived noise levels for Gaussian and Laplace mechanisms improve privacy guarantees.

Abstract

Pufferfish privacy (PP) is a generalization of differential privacy (DP), that offers flexibility in specifying sensitive information and integrates domain knowledge into the privacy definition. Inspired by the illuminating formulation of DP in terms of mutual information due to Cuff and Yu, this work explores PP through the lens of information theory. We provide an information-theoretic formulation of PP, termed mutual information PP (MI PP), in terms of the conditional mutual information between the mechanism and the secret, given the public information. We show that MI PP is implied by the regular PP and characterize conditions under which the reverse implication is also true, recovering the relationship between DP and its information-theoretic variant as a special case. We establish convexity, composability, and post-processing properties for MI PP mechanisms and derive noise levels for the Gaussian and Laplace mechanisms. The obtained mechanisms are applicable under relaxed assumptions and provide improved noise levels in some regimes. Lastly, applications to auditing privacy frameworks, statistical inference tasks, and algorithm stability are explored.