电子学报

• •    

基于本地化差分隐私的时序位置发布方案研究

康海燕, 冀源蕊   

  1. 北京信息科技大学信息管理学院信息安全系 北京 100192
  • 收稿日期:2021-10-28 修回日期:2022-02-18 出版日期:2022-05-30
  • 作者简介:康海燕 男,1971年7月生,河北石家庄人,博士,教授,北京信息科技大学信息管理学院副院长,研究方向为网络安全与隐私保护等. E-mail: kanghaiyan@126.com
    冀源蕊 女,1997年11月生,宁夏银川人,北京信息科技大学网络空间安全专业在读硕士研究生,研究方向为网络安全与隐私保护.
  • 基金资助:
    国家社科基金年度项目(21BTQ079);教育部人文社科项目(20YJAZH046);国家自然科学基金项目(61370139)

Research on Time-Serial Location Data Publication Based on Local Differential Privacy

KANG Hai-yan, JI Yuan-rui   

  1. School of Information Management,Beijing Information Science and Technology University,Beijing 100192,China
  • Received:2021-10-28 Revised:2022-02-18 Online:2022-05-30

摘要:

为了解决基于位置的服务(Location Based Service, LBS)在收集用户位置数据时造成的隐私泄露,提出一种本地化差分隐私位置发布模型. 首先,该模型采用了灵活的位置隐私保护方案(个性化隐私设置),即由用户选择已设定的多种隐私策略或定制隐私策略,在此基础上设计了定制隐私策略位置扰动算法(Customized Privacy policy Location Perturbation algorithm, CPLP);其次,提出并设计一种基于隐马尔可夫模型的时序关联位置隐私发布算法(Temporal Relational Location Privacy publishing algorithm,TRLP),解决发布时序位置时产生的隐私泄露;最后,在GeoLife数据集和Gowalla数据集上通过对比实验验证了该模型的有效性.

关键词: 差分隐私, 位置服务, 时序数据, 隐私发布, 隐马尔可夫模型

Abstract:

In order to solve the privacy leakage problem in Location Based Service (LBS) when collecting user's location data, we proposed a time-serial location data publication model based on local differential privacy. Firstly, the model adapts a flexible location privacy preservation method, allows users to choose or customize their privacy policy(personalized privacy Settings), based on customized privacy policy, we designed a Customized Privacy policy Location Perturbation algorithm(CPLP); Secondly, we proposed and designed Temporal Relational Location Privacy publishing algorithm(TRLP) based on Hidden Markov Model(HMM), which can reduce the privacy leakage when releasing the time-serial location data. Finally, we verified the usability of the algorithm on data sets Geolife and Gowalla.

Key words: differential privacy, location based service, time-series data, privacy releasing, hidden markov model

中图分类号: