부산대학교 도서관

Many mobile apps access users’ trajectories to provide critical services (e.g., trip tracking). Unfortunately, in such apps, malicious users may upload fake trajectories to cheat providers for illegal benefits. There are few works in the literature that delicately study trajectory forgery problems. In this paper, we first take the perspective of attackers and consider how they would fabricate vivid trajectories confronting a strict provider. In particular, we use the technique of adversarial examples in deep learning to propose a trajectory forgery method, which produces fake trajectories satisfying two conditions: (1) having the motion characteristics indistinguishable from those of real ones, and (2) matching reasonable walking, cycling, or driving routes when being projected to the map. Our experiments show that they can hardly be detected by mainstream trajectory service providers, even after being equipped with machine learning-based approaches. Therefore, we further present dedicated countermeasures by validating the reasonability of reported received signal strength indicator (RSSI) data of scanned WiFi APs in commercial areas and scanned Cellular APs in rural areas, respectively. They can deal well with the most challenging replay scenario, which can hardly be handled by existing radio-based location verification methods. We conduct extensive real-world experiments covering walking, cycling, and driving scenarios to demonstrate the high detection accuracy of both methods.