基于转移概率的位置隐私保护算法  

Location privacy protection algorithm based on transition probability

作　　者：彭妍婷 王庆生 PENG Yan-ting;WANG Qing-sheng(College of Information and Computer,Taiyuan University of Technology,Jinzhong 030600,China)

机构地区：[1]太原理工大学信息与计算机学院,山西晋中030600

出　　处：《计算机工程与设计》2023年第7期1993-1999,共7页Computer Engineering and Design

基　　金：山西省重点研发计划基金项目(高新技术领域)(201903D121121)。

摘　　要：基于位置的服务(location based service,LBS)得到了广泛应用,同时,用户的位置数据面临着巨大的隐私风险。因此,针对现有位置隐私方法中存在攻击者通过分析用户移动模式降低用户位置匿名度的问题,提出基于转移概率的位置隐私保护算法,通过马尔可夫链对用户的移动模式建模得到用户的转移概率,根据转移概率构建最优保护位置集,用策略图形式化保护位置集,通过拉普拉斯机制发布最优位置。通过实验分析,所提算法在保证用户位置隐私和发布效用的同时,拥有较低的时间成本。Location-based service(LBS)has been widely used.At the same time,the user’s location data are exposed to huge privacy risks.Therefore,in view of the problem that attackers reduce the anonymity of users’location by analyzing users’movement patterns in existing location privacy methods,a location privacy protection algorithm based on transition probability was proposed.The transition probability of users was obtained by modeling users’movement patterns with Markov chain,and the optimal protection location set was constructed according to the transition probability of users.The protection location set was formalized with policy graph,and the optimal location was published through Laplace mechanism.Through experimental analysis,the proposed algorithm has lower time cost while ensuring the privacy of users’location and publishing utility.

关 键 词：位置隐私 基于位置的服务 马尔可夫链 转移概率 差分隐私 策略图 位置发布 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]