Research On Personalized Privacy Protection Methods Based On Spatiotemporal Data

With the rapid development of the Internet and mobile technology,various applications based on location-based services have been gradually popularized by social networking platforms at home and abroad,such as Sina Weibo,Gowalla,etc.,are also provided based on location services.To users with rich social functions and social experiences at the same time,also store a lot of private temporal and spatial profiles in the shared information,such as ID,message related with time or position,etc.These personal data have potential privacy leakage risks.How to protect users’ sensitive information in the spatiotemporal environment of social networks has becoming an urgent problem to be solved.At the same time,different users may have different privacy proposals,which should be fully considered in the study of privacy protection of social networks.To solve the above problems,a personalized privacy protection method based on spatiotemporal data was proposed.Firstly,a Reliability-based Personalized Privacy Control Model(RPPCM)is proposed.Considering the possibility of privacy leakage of users’ spatiotemporal data in social networks,the reliability of users’ social association is calculated,and then the personalized control model RPPCM based on credibility is constructed.The model not only meets users’ personalized needs,but also effectively protects the sensitive information in the temporal and spatial data of users’ publishing,and balances the relationship between privacy protection and publishing quality.Then we design a Personalized Spatiotemporal Privacy Algorithm(PS-TPA).According to the proposed RPPCM model,the algorithm determines whether there is a risk of privacy leakage for the spatiotemporal data to be published by the user based on the user’s credibility.Our algorithm can evaluate the spatiotemporal interest positions that may leak privacy according to the reliability calculation,and feedback to users,that can reasonably meet the personalized needs of users,and reduce the risk of user privacy leakage.Secondly,in order to further meet the needs of users who want to continue to publish spatiotemporal data,this paper adds S-TGES model and algorithm based on spatiotemporal data.S-TGES service uses queue mechanism,grid encryption technology and the reprocessing and arrangement method of users’ spatiotemporal data based on random walk,finally realizes the spatiotemporal data protection algorithm based on grid encryption,and strengthens the personalized protection of users’ privacy interest points that they want to continue to publish.At the same time,the privacy protection degree in S-TGES algorithm adheres to the idea of credibility,can still maintain the personalized needs of users,and improve the protection of spatiotemporal data.Finally,this paper verifies the PS-TPA algorithm,and evaluates the effectiveness of privacy protection methods and the availability of personalized services.The real spatiotemporal data collected from Gowalla social network is taken as the experimental data set.The analysis of the experimental results shows that the algorithm can effectively protect the privacy of spatiotemporal data while ensuring the availability of the service while meeting the personalized privacy needs of users.In this paper,the effect of S-TGES algorithm is evaluated through experiments.The control experiment is based on the privacy protection method based on K-anonymity,and the real space-time data of Gowalla social network is taken as the data set.After calculating and identifying user privacy interest points.The effectiveness of the service is evaluated by the success rate of S-TGES algorithm,data availability after encryption and data processing time.Experimental results show that S-TGES algorithm has better privacy protection effect while ensuring users’ personalized privacy requirements.