基于指数机制的轨迹差分隐私保护方法

doi:10.11959/j.issn.2096-0271.2022042

摘要/Abstract

摘要： 针对传统轨迹数据保护中忽略位置点携带的语义信息带来的隐私泄露问题，本文提出一种基于指数机制的差分隐私轨迹保护方法。本文根据差分隐私中指数机制的特性，同时考虑地理特征以及位置语义特征双重属性信息导致的隐私泄露，对位置点设计可用的打分函数后随机化输出，对轨迹进行了有效的隐私保护。该方案使得在保证位置隐私的同时减小数据集规模，同时可以防止语义背景推断攻击，提高数据可用性。本文在真实轨迹数据集上进行了实验，实验结果表明该方法在保证隐私强度下，既有效保护了用户的停留区域位置隐私，同时有效的提高了数据可用性。

关键词: 差分隐私, 时空轨迹, 语义位置, 指数机制

Abstract: Aiming at the problem of privacy disclosure caused by ignoring semantic information carried by location points in traditional trajectory data protection, a differential privacy trajectory protection method based on exponential mechanism is proposed in this paper. According to the characteristics of the index mechanism in differential privacy, and considering the privacy disclosure caused by the dual attribute information of geographic features and semantic features of location, this paper designs an available scoring function for location points and then randomizes the output to effectively protect the trajectory privacy. This scheme can reduce the size of data sets while ensuring location privacy, prevent semantic background inference attacks and improve data availability. In this paper, experiments are carried out on real trajectory data sets, and the experimental results show that the proposed method not only effectively protects the privacy of the user's stay area location, but also effectively improves the data availability while ensuring the privacy intensity.

Key words: Differential privacy, Space-time trajectory, Semantic location, Index mechanis

焦荟聪, 刘文菊, 王赜. 基于指数机制的轨迹差分隐私保护方法[J]. 大数据, doi: 10.11959/j.issn.2096-0271.2022042.

JIAO Hui-cong, LIU Wen-ju, WANG Ze. Differential Privacy Protection method Based on Exponential Mechanism[J]. Big Data Research, doi: 10.11959/j.issn.2096-0271.2022042.

参考文献

[1] Huo Z, Meng X, Hu H, et al. You can walk alone: trajectory privacy-preserving through significant stays protection[C]//International conference on database systems for advanced applications. Springer, Berlin, Heidelberg, 2012: 351-366.
[2] Xinglan Zhang,Wenjin Yang. Trajectory Anonymous Algorithm Based on k -Means++ against Similarity Attack[J]. Computer Science and Application, 2020, 10(04) : 610-618.
[3] 俞望年,宣占祥,马小明,岳威,左开中.轨迹数据发布中基于敏感语义位置的隐私保护算法[J].现代计算机,2020(27):3-9.
[4] 俞庆英,王燕飞,叶梓彤,张双桂,陈传明.基于优化局部抑制的轨迹数据发布隐私保护算法[J].计算机工程,2020,46(08):112-118.
[5] 王辉,朱国宇,申自浩,刘琨,刘沛骞.基于用户偏好和位置分布的假位置生成方法[J].计算机科学,2021,48(07):164-171.
[6] Yu Wangnian, Xuan Zhanxiang, Ma Xiaoming, Yue Wei, Zuo Kaizhong. Privacy Protection algorithm based on sensitive semantic location in trajectory data publishing [J]. Modern Computers,2020(27):3-9.
[7] Yu Qing-ying, WANG Yan-fei, YE Zi-tong, ZHANG Shuang-Gui, Chen Chuan-ming. Trajectory data publishing privacy protection algorithm based on optimized local suppression [J]. Computer engineering,2020,46(08):112-118.
[8] 霍峥,孟小峰.一种满足差分隐私的轨迹数据发布方法[J].计算机学报,2018,41(02):400-412.
[9] 刘向宇,刘竹丰,夏秀峰,李佳佳,宗传玉,朱睿.一种保持轨迹数据高可用性的隐式位置访问隐私保护技术[J].沈阳航空航天大学学报,2019,36(02):66-75.
[10] Peng Changgen, DING Hongfa, Zhu Yijie, TIAN Youliang, Fu Zufeng. Journal of software,2016,27(08):1891-1903.]
[11] Visvalingam M ,Whyatt J D . Line generalisation by repeated elimination of points[J]. Cartographic Journal, 1993, 30(1):46-51.
[12] Dwork C . Calibrating noise to sensitivity in private data analysis[J]. Lecture Notes in Computer Science, 2012, 3876(8):265-284.
[13] Mcsherry F ,Talwar K . Mechanism Design via Differential Privacy[C]// Foundations of Computer Science, 2007. 48th Annual IEEE Symposium on. IEEE, 2007:94-103.
[14] Sandor M. Veres. Relations between information criteria for model-structure selection Part 2. Modelling by shortest data description[J]. International Journal of Control, 1990, 52(2) : 409-421.
[15] Myers C S , Rabiner L R . A comparative study of several dynamic time warping algorithms for speech recognition[J]. Bell Labs Technical Journal, 2013, 60(7):1389-1409.
[16] Jiang K, Shao D, Bressan S, et al. Publishing trajectories with differential privacy guarantees[C]//Proceedings of the 25th International Conference on Scientific and Statistical Database Management. 2013: 1-12.
[17] 兰微,林英,包聆言,李彤,陈梦蓉,单今朝.融入兴趣区域的差分隐私轨迹数据保护方法[J].计算机科学与探索,2020,14(01):59-72.
[18] Lee J G, Han J, Whang K Y. Trajectory clustering: a partition-and-group framework[C]//Proceedings of the 2007 ACM SIGMOD international conference on Management of data. 2007: 593-604.
[19] 马明杰, 杜跃进, 李凤华,等. 基于语义的位置服务隐私保护综述[J]. 网络与信息安全学报, 2016, 2(12):11.