摘要：Due to the advances of mobile devices with GPS (Global Positioning System), a user's privacy threat is increased in location based services (LBSs).So, various Location Privacy-Preserving Mechanisms (LPPMs) have been proposed in the literature to address the privacy risks derived from the exposure of user locations through the use of LBSs. However, these methods obfuscate the locations disclosed to the LBS provider using a variety of strategies, most of which come at a cost of resource consumption. Therefore, we propose a privacy-protected KNN query anonymization method based on Bayesian estimation for Location-based services. Unlike previous dummy-based approaches, in our method, the request to the LBS server doesn't contain the genuine user location, so we can't calculate whether meet the threshold condition of two location directly, but must to decision making by transition probability. In addition, our method just requires the server returns the results the client needs. Further, we propose an effective search algorithm to improve the server processing. So it can reduce bandwidth usages and efficiently support K-nearest neighbor queries without revealing the private information of the query issuer. An empirical study shows that our proposal is effective in terms of offering location privacy, and efficient in terms of computation and communication costs.
