Method for protecting privacy of wifi fingerprint indoor positioning system through utilization of differential privacy

Abstract

The invention discloses a method for protecting privacy of a wifi fingerprint indoor positioning system through utilization of differential privacy. The method comprises the steps of collecting a real-time wifi fingerprint at a to-be-positioned user side, wherein the real-time wifi fingerprint comprises an access point AP name and corresponding received signal strength RSS, and sending an AP sequence to a server; selecting fingerprint records with the same AP sequence from a database by the server according to the AP sequence sent by the user side, thereby forming a fingerprint data set; carrying out iterative clustering on sample point positions of the fingerprint records and carrying out noise addition processing in a clustering process, thereby forming k clusters; for each reference point position, replacing an original position by selecting a new position based on a probability, and sending the updated fingerprint data set back to a user; and calculating the Euclidean distance between the real-time fingerprint and the fingerprint in the received data set, at the user side, and estimating the position of the user through adoption of an improved KNN method. According to the method, the data availability is ensued and moreover, the data privacy is protected. For the user side, through application of the method, the position privacy of the user can be protected.

Description

technical field [0001] The invention belongs to the technical field of data release, and in particular relates to a method for protecting the privacy of a WifiFingerprint indoor positioning system by using differential privacy. Background technique [0002] Indoor positioning based on Wifi Fingerprint is recognized as one of the most promising technologies in the field of indoor positioning. The location of the user terminal is estimated by comparing the real-time collected fingerprint (Wifi signal strength) with the fingerprint stored in the database. The advantages are obvious, low cost and high reliability can be achieved. However, potential privacy issues cannot be ignored. The location information of the client and the data privacy of the server database may be leaked during the positioning process. [0003] Traditional privacy protection methods include homomorphic encryption technology and anonymous processing. Homomorphic encryption, such as Paillier encryption, ha...

AI Technical Summary

Problems solved by technology

But the disadvantage of this invention is that the attacker can obtain the approximate information of the database through brute-force, that is, the attacker forges as many WiFi fingerprints as possible within the legal range, and uses this scheme to obtain the positioning results of all WiFi fingerprints. When the position of the reference point in the index set is the same, the database composed of these positioning results and the corresponding pseudo WiFi fingerprint is very similar to the original database.

Images