ITLGOct 2, 2017

Privacy with Estimation Guarantees

arXiv:1710.00447v553 citations
Originality Incremental advance
AI Analysis

This addresses the central problem of balancing privacy and utility for data owners and analysts, but it is incremental as it builds on existing estimation-theoretic frameworks.

The paper tackles the privacy-utility trade-off in data sharing by analyzing how to allow reconstruction of certain data functions for utility while preventing others for privacy, using chi-square information to bound this trade-off and proposing a convex program for computing privacy-assuring mappings.

We study the central problem in data privacy: how to share data with an analyst while providing both privacy and utility guarantees to the user that owns the data. In this setting, we present an estimation-theoretic analysis of the privacy-utility trade-off (PUT). Here, an analyst is allowed to reconstruct (in a mean-squared error sense) certain functions of the data (utility), while other private functions should not be reconstructed with distortion below a certain threshold (privacy). We demonstrate how chi-square information captures the fundamental PUT in this case and provide bounds for the best PUT. We propose a convex program to compute privacy-assuring mappings when the functions to be disclosed and hidden are known a priori and the data distribution is known. We derive lower bounds on the minimum mean-squared error of estimating a target function from the disclosed data and evaluate the robustness of our approach when an empirical distribution is used to compute the privacy-assuring mappings instead of the true data distribution. We illustrate the proposed approach through two numerical experiments.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes