基于边介数模型的差分隐私保护方案

doi:10.11959/j.issn.1000-436x.2019095

通信学报 ›› 2019, Vol. 40 ›› Issue (5): 88-97.doi: 10.11959/j.issn.1000-436x.2019095

基于边介数模型的差分隐私保护方案

黄海平^1,²,王凯^1,²,汤雄^1,²,张东军^1,²

¹ 南京邮电大学计算机学院，江苏南京 210023
² 江苏省无线传感网高技术研究重点实验室，江苏南京 210023

修回日期:2019-03-21 出版日期:2019-05-25 发布日期:2019-05-30
作者简介:黄海平（1981- ），男，福建三明人，博士，南京邮电大学计算机学院教授、副院长，主要研究方向为物联网安全和数据隐私保护等。|王凯（1994- ），男，江苏扬州人，南京邮电大学硕士生，主要研究方向为物联网安全和数据隐私保护。|汤雄（1992- ），男，江苏沭阳人，南京邮电大学硕士生，主要研究方向为物联网安全和数据隐私保护。|张东军（1993- ），男，江苏徐州人，南京邮电大学硕士生，主要研究方向为物联网安全和数据隐私保护。
基金资助:
国家自然科学基金资助项目(61672297);江苏省重点研发计划（社会发展）基金资助项目(BE2017742);江苏省六大人才高峰基金资助项目(DZXX-017)

Differential privacy protection scheme based on edge betweenness model

Haiping HUANG^1,²,Kai WANG^1,²,Xiong TANG^1,²,Dongjun ZHANG^1,²

¹ College of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
² High Technology Research Key Laboratory of Wireless Sensor Network of Jiangsu Province,Nanjing 210023,China

Revised:2019-03-21 Online:2019-05-25 Published:2019-05-30
Supported by:
The National Natural Science Foundation of China(61672297);The Key Research and Development Program of Jiangsu Province (Social Development Program)(BE2017742);The Sixth Talent Peaks Project of Jiangsu Province in China(DZXX-017)

摘要/Abstract

摘要：

随着社交网络应用的不断发展，用户社交关系等个人隐私数据的安全保护问题亟待解决。为显著减小社交网络数据的敏感度，提出了一种基于边介数模型的差分隐私保护方案 BCPA。基于 dK 模型捕获图结构对应的2K 序列，根据边中介中心性系数对 2K 序列重新排序；依据排序结果将 2K 序列聚类成多个子序列，再利用 dK扰动算法对各子序列分别进行加噪；根据整合后的新 2K 序列生成满足差分隐私的社交网络发布图。基于真实数据集，通过模拟仿真将所提方案与其他经典方案进行比较，实验结果表明，所提方案在保证较强隐私保护性的同时，提高了发布数据的准确性和可用性。

关键词: 社交网络, 隐私保护, 差分隐私, dK模型, 聚类, 分组扰动

Abstract:

With the continuous development of social network application,user’s personal social data is so sensitive that the problem of privacy protection needs to be solved urgently.In order to reduce the network data sensitivity,a differential privacy protection scheme BCPA based on edge betweenness model was proposed.The 2K sequence corresponding to the graph structure based on the dK model was captured,and 2K sequences based on the edge betweenness centrality were reordered.According to the result of reordering,the 2K sequence was grouped into several sub-sequences,and each sub-sequence was respectively added with noise by a dK perturbation algorithm.Finally,a social network graph satisfying differential privacy was generated according to the new 2K sequences after integration.Based on the real datasets,the scheme was compared with the classical schemes through simulation experiments.The results demonstrate that it improves the accuracy and usability of data while ensuring desired privacy protection level.

Key words: social network, privacy protection, differential privacy, dK model, clustering, group perturbation

中图分类号:

TP309

黄海平,王凯,汤雄,张东军. 基于边介数模型的差分隐私保护方案[J]. 通信学报, 2019, 40(5): 88-97.

Haiping HUANG,Kai WANG,Xiong TANG,Dongjun ZHANG. Differential privacy protection scheme based on edge betweenness model[J]. Journal on Communications, 2019, 40(5): 88-97.

图/表 6

图1

表1

图2

图3

图4

图5

参考文献 16

[1]	WANG Q , ZHANG Y , REN K ,et al. Real-time and spatio-temporal crowd-sourced social network data publishing with differential privacy[J]. IEEE Transactions on Dependable and Secure Computing, 2018,15(4): 591-606.
[2]	DWORK C , . Differemtial privacy[C]// Proceedings of the 33rd International Colloquium on Automata,Language and Programming(ICALP). 2006: 1-12.
[3]	CASAS-ROMA J , HERRERA-JOANCOMARTI J , TORRA V . k-Degree anonymity and edge selection:improving data utility in large networks[J]. Knowledge ＆ Information Systems, 2016,50(2): 1-28.
[4]	HAY M , LI C , MIKLAU G ,et al. Accurate estimation of the degree distribution of private networks[C]// Ninth IEEE International Conference on Data Mining. 2009: 169-178.
[5]	MIR D J , WRIGHT R N . A differentially private graph estimator[C]// IEEE International Conference on Data Mining Workshops. IEEE, 2009: 122-129.
[6]	LESKOVEC J , FALOUTSOS C . Scalable modeling of real graphs using Kronecker multiplication[C]// Machine Learning,Proceedings of the Twenty-Fourth International Conference. 2007: 497-504.
[7]	DAY W Y , LI N , MIN L . Publishing graph degree distribution with node differential privacy[C]// ACM International Conference on Management of Data(SIGMOD). 2016: 123-138.
[8]	SALA A , ZHAO X , Wilson C ,et al. Sharing graphs using differentially private graph models[C]// The 11th ACM SIGCOMM Internet Measurement Conference. 2011: 81-98.
[9]	WANG Y , WU X . Preserving differential privacy in degree-correlation based graph generation[J]. Transactions on Data Privacy, 2013,6(2): 127-145.
[10]	兰丽辉, 鞠时光 . 基于差分隐私的权重社会网络隐私保护[J]. 通信学报, 2015,36(9): 145-159.
	LAN L H , JU S G . Privacy preserving based on differential privacy for weighted social networks[J]. Journal on Communications, 2015,36(9): 145-159.
[11]	FU Y , CHEN Z , KORU G ,et al. A privacy protection technique for publishing data mining models and research data[J]. ACM Transactions on Management Information Systems, 2010,1(1): 1-20.
[12]	熊文君, 徐正全, 王豪 . 基于滤波原理的时间序列差分隐私保护强度评估[J]. 通信学报, 2017,38(5): 172-181.
	XIONG W J , XU Z Q , WANG H . Privacy level evaluation of differential privacy for time series based on filtering theory[J]. Journal on Communications, 2017,38(5): 172-181.
[13]	DWORK C , MCSHERRY F , NISSIM K ,et al. Calibrating noise to sensitivity in private data analysis[C]// The Third Theory of Cryptography Conference, 2006: 265-284.
[14]	MCSHERRY F , . Privacy integrated queries:an extensible platform for privacy-preserving data analysis[C]// The 2009 ACM SIGMOD International Conference on Management of Data. 2009: 19-30.
[15]	JAMOUR F , SKIADOPOULOS S , KALNIS P . Parallel algorithm for incremental betweenness centrality on large graphs[J]. IEEE Transactions on Parallel and Distributed Systems, 2018,29(3): 659-672.
[16]	MUHONGYA K , MAHARAJ M . Visualising and analysing online social networks[C]// International Conference on Computing,Communication and Security(ICCCS). 2016: 1-6.

名称	节点数	边数
wiki-Vote	7 115	103 689
ego-Twitter	81 306	1 768 149

基于边介数模型的差分隐私保护方案

Differential privacy protection scheme based on edge betweenness model

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 16

相关文章 15

Metrics

推荐阅读 0

[1]	马玲, 樊漆亮, 许婷, 郭冠琛, 张圣林, 孙永谦, 张玉志. 基于强化学习的在线离线混部云环境下的调度框架[J]. 通信学报, 2023, 44(6): 90-102.
[2]	马鑫迪, 李清华, 姜奇, 马卓, 高胜, 田有亮, 马建峰. 面向Non-IID数据的拜占庭鲁棒联邦学习[J]. 通信学报, 2023, 44(6): 138-153.
[3]	冯涛, 陈李秋, 方君丽, 石建明. 基于本地化差分隐私和属性基可搜索加密的区块链数据共享方案[J]. 通信学报, 2023, 44(5): 224-233.
[4]	余晟兴, 陈泽凯, 陈钟, 刘西蒙. DAGUARD：联邦学习下的分布式后门攻击防御方案[J]. 通信学报, 2023, 44(5): 110-122.
[5]	夏莹杰, 朱思雨, 刘雪娇. 区块链架构下具有条件隐私的车辆编队跨信任域高效群组认证研究[J]. 通信学报, 2023, 44(4): 111-123.
[6]	胡柏吉, 张晓娟, 李元诚, 赖荣鑫. 支持多功能的V2G网络隐私保护数据聚合方案[J]. 通信学报, 2023, 44(4): 187-200.
[7]	徐明, 张保俊, 伍益明, 应晨铎, 郑宁. 面向网络攻击和隐私保护的多智能体系统分布式共识算法[J]. 通信学报, 2023, 44(3): 117-127.
[8]	董煜, 张友鹏. 基于聚类赋权的冲突证据组合方法[J]. 通信学报, 2023, 44(3): 157-163.
[9]	张淑芬, 董燕灵, 徐精诚, 王豪石. 基于目标扰动的AdaBoost算法[J]. 通信学报, 2023, 44(2): 198-209.
[10]	余晟兴, 陈钟. 基于同态加密的高效安全联邦学习聚合框架[J]. 通信学报, 2023, 44(1): 14-28.
[11]	汤凌韬, 王迪, 刘盛云. 面向非独立同分布数据的联邦学习数据增强方案[J]. 通信学报, 2023, 44(1): 164-176.
[12]	袁程胜, 郭强, 付章杰. 基于差分隐私的深度伪造指纹检测模型版权保护算法[J]. 通信学报, 2022, 43(9): 181-193.
[13]	赵静, 李俊, 龙春, 万巍, 魏金侠, 陈凯. 基于多层次特征的RoQ隐蔽攻击无监督检测方法[J]. 通信学报, 2022, 43(9): 224-239.
[14]	王瀚仪, 李效光, 毕文卿, 陈亚虹, 李凤华, 牛犇. 多级本地化差分隐私算法推荐框架[J]. 通信学报, 2022, 43(8): 52-64.
[15]	张学旺, 黎志鸿, 林金朝. 基于公平盲签名和分级加密的联盟链隐私保护方案[J]. 通信学报, 2022, 43(8): 131-141.