Robust Privatization with Multiple Tasks and the Optimal Privacy-Utility Tradeoff

TL;DR

This paper investigates the fundamental limits and optimal mechanisms for privacy-preserving data release that balances privacy leakage and utility across multiple tasks, providing explicit solutions and robustness analysis.

Contribution

It introduces a novel framework for multi-task privacy mechanisms, deriving explicit solutions and decomposing complex problems into parallel privacy funnel subproblems.

Findings

Optimal privacy-utility tradeoff characterized by a leakage-free threshold.

Decomposition of non-convex optimization into parallel privacy funnel problems.

Explicit solutions for private feature protection with deterministic data components.

Abstract

In this work, fundamental limits and optimal mechanisms of privacy-preserving data release that aims to minimize the privacy leakage under utility constraints of a set of multiple tasks are investigated. While the private feature to be protected is typically determined and known by the sanitizer, the target task is usually unknown. To address the lack of information on the specific task, utility constraints laid on a set of multiple possible tasks are considered. The mechanism protects the specific privacy feature of the to-be-released data while satisfying utility constraints of all possible tasks in the set. First, the single-letter characterization of the rate-leakage-distortion region is derived, where the utility of each task is measured by a distortion function. It turns out that the minimum privacy leakage problem with log-loss distortion constraints and the unconstrained released rate is a non-convex optimization problem. Second, focusing on the case where the raw data consists of multiple independent components, we show that the above non-convex optimization problem can be decomposed into multiple parallel privacy funnel (PF) problems with different weightings. We explicitly derive the optimal solution to each PF problem when the private feature is a component-wise deterministic function of a data vector. The solution is characterized by a leakage-free threshold: when the utility constraint is below the threshold, the minimum leakage is zero; once the required utility level is above the threshold, the privacy leakage increases linearly. Finally, we show that the optimal weighting of each privacy funnel problem can be found by solving a linear program (LP). A sufficient released rate to achieve the minimum leakage is also derived. Numerical results are shown to illustrate the robustness of our approach against the task non-specificity.