基于连续查询的语义位置隐私保护算法  

Semantic location privacy protection algorithm based on continuous query

作　　者：贾媛媛 史志才[1,2] 方凯 JIA Yuanyuan;SHI Zhicai;FANG Kai(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China;Shanghai Key Laboratory of Integrated Administration Technologies for Information Security,Shanghai 200240,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620 [2]上海市信息安全综合管理技术研究重点实验室,上海200240

出　　处：《智能计算机与应用》2021年第7期156-161,165,共7页Intelligent Computer and Applications

基　　金：上海市信息安全综合管理技术研究重点实验室开放研究课题基金(AGK2019004)。

摘　　要：针对用户连续位置查询请求服务中未考虑语义信息而导致用户敏感语义泄露问题,为了实现对道路网络上客户端的查询隐私、位置隐私和语义位置隐私保护,本文提出一种离线轨迹聚类和语义位置图相结合的算法来进行隐藏用户的选择,使隐藏用户的位置具有明显的多样性和不同的语义以及多样化的服务请求,有效保护客户端的语义和位置隐私。在具有2个定义指标的真实地图上评估了该算法的有效性,整个连续查询道路网络服务的过程中,有很好的成功率和查询处理时间。同时与现有的其他可信第三方模型算法进行了对比分析,验证了本文算法的有效性。Since the user's continuous location query request service without considering semantic information,to realize the protection of query privacy,location privacy and semantic location privacy of the client on the road network,this paper proposes an algorithm of offline trajectory clustering and semantic location map to choose hidden users,so that the hidden users'locations have obvious diversity,different semantics and diversified service requests effectively protect the semantics and location privacy of the client.The effectiveness of the algorithm is evaluated on a real map with two defined indicators,the entire process of continuously querying road network services has a very good success rate and query processing time.At the same time,compared with other trusted third-party model algorithms,the validity of this algorithm is verified.

关 键 词：位置隐私保护 连续查询 轨迹聚类 语义位置图 语义位置隐私 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]