Processing uncertain spatial data resulting from differentially-private sanitization

Abstract

The unprecedented revolution in mobile computing provides users with the ability to participate in applications that are customized to their spatial coordinates. Location-based social media and location-based recommendations are only two examples of popular scenarios where the use of geographical location can significantly improve user experience. However, serious privacy concerns arise when sharing users' locations, as an adversary may be able to derive sensitive personal details from one's whereabouts, such as health status, political or religious orientation, alternative lifestyles, etc. Privacy models such as differential privacy (DP) are commonly employed to protect individuals' whereabouts before sharing. Typically, privacy is achieved by introducing uncertainty with respect to a user's location. In this setting, uncertain data processing techniques become a natural choice for processing user location data that have been previously sanitized to protect privacy. In this article, we discuss some prominent scenarios where it is important to protect location data, and we explain how the de-facto standard of differentially-private location protection can be used in conjunction with uncertain data processing. We also look at a highly promising use case scenario of interest, namely privacy-preserving spatial crowd-sourcing, and provide an overview of how DP and uncertain data processing are combined to address this problem.