基于高效假轨迹的隐私保护算法研究  

Research on privacy protection algorithm based on efficient fake trajectory

作　　者：王海涛[1] 田可可 王辉[1] 刘静[1] Wang Haitao;Tian Keke;Wang Hui;Liu Jing(School of Computer Science&Technology,Henan Polytechnic University,Jiaozuo Henan 454003,China)

机构地区：[1]河南理工大学计算机科学与技术学院,河南焦作454003

出　　处：《计算机应用研究》2021年第4期1175-1178,1184,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(11601129,61503124)。

摘　　要：为了解决LBS服务中用户轨迹隐私泄露的问题,提出了一种基于高效假轨迹的隐私保护算法。首先,该方案综合考虑用户所处区域的背景信息,以划分网格的方式,统计每个网格的历史服务请求概率,确保生成的每一个假位置与对应真实位置具有相同的历史服务请求概率;其次,结合网格历史服务请求概率并通过万有引力定律模型计算出用户位置转移概率;最后,生成与真实位置转移概率最相近的k-1条假轨迹实现K-匿名。实验结果表明,该方案能够更有效地保护用户的轨迹隐私。In order to solve the problem of privacy leakage of user trajectories in the LBS service,this paper proposed a privacy protection algorithm based on efficient false trajectories.First,the scheme comprehensively considered the background information of the area where the user was located,calculated the historical service request probability of each grid in a grid-divided manner,and ensured that each generated fake location had the same historical service request as the corresponding real location probability.Secondly,it combined the grid historical service request probability and the gravitational law model calculated the user location transfer probability.Finally,it generated k-1 fake trajectories with the closest probabilities of real position transition to achieve K-anonymity.Experimental results show that this scheme can protect the users trajectory privacy more effectively.

关 键 词：位置服务 轨迹隐私 背景信息 历史服务请求概率 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]