Journal of Applied Sciences ›› 2019, Vol. 37 ›› Issue (6): 835-843.doi: 10.3969/j.issn.0255-8297.2019.06.008

• Signal and Information Processing • Previous Articles     Next Articles

Trajectory Privacy Protection Method Using LSTM Network

YAN Shaojun, WANG Zichi, ZHANG Xinpeng   

  1. School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
  • Received:2018-12-19 Revised:2019-03-13 Online:2019-11-30 Published:2019-12-06

Abstract: With the popularity of the mobile Internet, location query has become an important way for users to enjoy services. However, in the location query, the server can obtain the user location and trajectory information, which threaten the user's privacy. In order to improve the privacy of user trajectory, this paper proposes a method to protect user trajectory privacy by using improved long short-term memory (LSTM) networks. First, the trusted third party uses the improved LSTM network to predict the later position of the user. While constructing the anonymous area, the third party places the predicted location point information into the current moment to make a request. It can disrupt the timing information in the trajectory and obscure the user trajectory sequence on the server side, and therefore protects the privacy of user trajectory. Meanwhile, by placing the future moments into the current moment, the unreasonable problem of the anonymous area in the location privacy protection is overcome. Thus, the effectiveness of the system service is ensured. Experimental results show that the privacy of the user trajectory in this method is better than existing method.

Key words: trajectory, privacy protection, long short-term memory (LSTM), locationbased service

CLC Number: