Location Trace Privacy Under Conditional Priors

TL;DR

This paper introduces a Rényi divergence-based privacy framework tailored for location data with conditional dependencies, providing a method to limit privacy loss in location traces under Gaussian process priors.

Contribution

It presents a novel privacy framework for dependent location data and an algorithm to achieve privacy guarantees under Gaussian process models.

Findings

Framework effectively bounds privacy loss in dependent location data

Algorithm achieves privacy within a fixed radius for sensitive locations

Highlights challenges of protecting conditionally dependent data

Abstract

Providing meaningful privacy to users of location based services is particularly challenging when multiple locations are revealed in a short period of time. This is primarily due to the tremendous degree of dependence that can be anticipated between points. We propose a R\'enyi divergence based privacy framework for bounding expected privacy loss for conditionally dependent data. Additionally, we demonstrate an algorithm for achieving this privacy under Gaussian process conditional priors. This framework both exemplifies why conditionally dependent data is so challenging to protect and offers a strategy for preserving privacy to within a fixed radius for sensitive locations in a user's trace.