Location privacy for group meetups

Abstract

A Group Nearest Neighbor (GNN) query finds a point of interest (POI) that minimizes the aggregate distance for a group of users. In current systems, users have to reveal their exact, often sensitive locations to issue a GNN query. This calls for private GNN queries. However, existing methods for private GNN queries either are computationally too expensive for mobile phones or cannot resist sophisticated attacks. Our approach can efficiently and effectively process an important variant of private GNN queries: queries that minimize the maximum distance for any user in the group. To achieve high efficiency we develop a distributed multi-party private protocol to compute the maximum function. Our method exploits geometric constraints to prune POIs and avoids unnecessary data disclosure. In contrast to current state of the art multi-party private protocols, our proposed protocol does not rely on cryptography and has a fast runtime. Importantly, a user does not have to provide a location directly, even in imprecise form.