On the Anonymization of Differentially Private Location Obfuscation

TL;DR

This paper compares obfuscation mechanisms for location privacy, showing that the optimal geo-indistinguishable mechanism offers stronger anonymity and better utility than the planar Laplacian, with formal analysis and empirical validation.

Contribution

It introduces the concept of asymptotic anonymity and demonstrates that the optimal geo-indistinguishable mechanism enhances anonymity and utility over traditional methods.

Findings

Optimal geo-indistinguishable mechanism provides stronger k-anonymity.

Fewer users need to be removed for anonymization with the optimal mechanism.

The optimal mechanism offers better utility for users and data analysts.

Abstract

Obfuscation techniques in location-based services (LBSs) have been shown useful to hide the concrete locations of service users, whereas they do not necessarily provide the anonymity. We quantify the anonymity of the location data obfuscated by the planar Laplacian mechanism and that by the optimal geo-indistinguishable mechanism of Bordenabe et al. We empirically show that the latter provides stronger anonymity than the former in the sense that more users in the database satisfy k-anonymity. To formalize and analyze such approximate anonymity we introduce the notion of asymptotic anonymity. Then we show that the location data obfuscated by the optimal geo-indistinguishable mechanism can be anonymized by removing a smaller number of users from the database. Furthermore, we demonstrate that the optimal geo-indistinguishable mechanism has better utility both for users and for data analysts.