Scalable Optimization for Locally Relevant Geo-Location Privacy

Geo-obfuscation functions as a location privacy protection mechanism (LPPM), enabling mobile users to share obfuscated locations with servers instead of their exact locations. This technique protects users' location privacy during server-side data breaches since the obfuscation process is irreversible. To minimize the utility loss caused by data obfuscation, linear programming (LP) is widely used. However, LP can face a polynomial explosion in decision variables, making it impractical for large-scale geo-obfuscation applications. In this paper, we propose a new LPPM called Locally Relevant Geo-obfuscation (LR-Geo) to optimize geo-obfuscation using LP more efficiently. This is accomplished by restricting the geo-obfuscation calculations for each user to locally relevant (LR) locations near the user's actual location. To prevent LR locations from inadvertently revealing a user's true whereabouts, users compute the LP coefficients locally and upload only these coefficients to the server, rather than the LR locations themselves. The server then solves the LP problem using the provided coefficients. Additionally, we enhance the LP framework with an exponential obfuscation mechanism to ensure that the obfuscation distribution is indistinguishable across multiple users. By leveraging the constraint structure of the LP formulation, we apply Benders' decomposition to further boost computational efficiency. Our theoretical analysis confirms that, even though geo-obfuscation is calculated independently for each user, it still adheres to geo-indistinguishability constraints across multiple users with high probability. Finally, experimental results using a real-world dataset demonstrate that LR-Geo outperforms existing geo-obfuscation methods in terms of computational time, data utility, and privacy protection.