Location privacy preservation through kernel transformation

The frequent data leak scandals of recent years indicate that service providers who hold personal data may not be reliable as they claim. We assert that sensitive user information must be sanitized locally before it is sent to service providers if it is to be protected. The LPPK privacy-preserving framework presented in this article is a local sanitization scheme, for location-based services (LBSs). It applies a fog-computing structure in which a private map is generated by the LBS server with kernel transformation for each user. A fog device then provides location services for each user according to the private map. Without colluding, neither the LBS server nor the fog device can deduce a user's real location. Experiments conducted on real-world data sets demonstrate that LPPK delivers sufficient query accuracy at a level significantly higher than existing approaches while preserving location privacy.