基于特征轨迹点的位置隐私保护方案  

A location privacy protection scheme based on charac teristic trajectory points

作　　者：敖山[1] 黄朋阳 王辉[2] 申自浩[1] 刘沛骞 AO Shan;HUANG Pengyang;WANG Hui;SHEN Zihao;LIU Peiqian(School of Computer Science and Technology,Henan Polytechnic University,Jiaozuo 454000,P.R.China;School of Software,Henan Polytechnic University,Jiaozuo 454000,P.R.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454000 [2]河南理工大学软件学院,河南焦作454000

出　　处：《重庆邮电大学学报（自然科学版）》2024年第6期1140-1149,共10页Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61300216);河南省高等学校重点科研资助项目(23A520033);河南理工大学博士基金资助项目(B2022-16,B2020-32)。

摘　　要：针对现有位置隐私保护方案大多对轨迹上所有位置点都进行处理,导致数据处理效率低、可用性差的问题,提出一种基于特征轨迹点的位置隐私保护方案。将优化后的最小描述长度与迪杰斯特拉(Dijkstra)算法相结合,选择代表整个轨迹的特征轨迹点,实现最优的轨迹分割,以得到相似轨迹;采用优化后的DBSCAN密度聚类算法对相似轨迹进行处理,得到等价类;在保证隐私预算的前提下,从等价类中选择与用户真实特征轨迹点弗朗明歇距离(Fréchet distance)最小的混淆点,然后以时间序列连接这些点形成混淆轨迹。提出的方案对特征轨迹点进行保护,降低了数据的计算复杂度;通过选择与用户真实位置距离最小的混淆点,保证了数据可用性。与IFTS和TP-MALS两个方案进行对比分析表明,提出的方案既能提高数据处理效率,又能保证数据的可用性。Existing location privacy protection schemes often process all points on a trajectory,resulting in low data processing efficiency and poor usability.To address these issues,we propose a location privacy protection scheme based on characteristic trajectory points.This approach combines the optimized minimum description length with Dijkstra’s algorithm to select representative characteristic trajectory points,achieving optimal trajectory segmentation and generating similar trajectories.We employ an optimized DBSCAN density clustering algorithm to process these similar trajectories,resulting in equivalence classes.Under the constraint of privacy budget,we select confusion points from the equivalence classes that have the smallest Fréchet distance to the user’s actual characteristic trajectory points.These points are then connected in a time series to form confusion trajectories.By protecting characteristic trajectory points,the proposed scheme reduces the computational complexity of the data and ensures data usability by selecting confusion points closest to the user’s actual location.Comparative analysis with the IFTS and TP-MALS schemes shows that the proposed scheme enhances data processing efficiency while ensuring data usability.

关 键 词：位置隐私 最小描述长度 轨迹分割 弗朗明歇距离 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]