JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE) ›› 2019, Vol. 54 ›› Issue (3): 10-17, 27.doi: 10.6040/j.issn.1671-9352.2.2018.084

•   • Previous Articles     Next Articles

Sensitive attribute iterative inference method for social network users

Xiao-jie XIE1,2(),Ying LIANG1,*(),Xiang-xiang DONG1,2   

  1. 1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
    2. School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2018-09-20 Online:2019-03-20 Published:2019-03-19
  • Contact: Ying LIANG E-mail:mailbox_of_xxj@126.com;liangy@ict.ac.cn
  • Supported by:
    国家重点研发计划(2018YFB1004704);国家重点研发计划(2016YFB0800403)

RichHTML

18

PDF (PC)

462

Abstract:

Analyzing and inferring sensitive information of social network users is conducive to technically quantifying the degree of privacy leakage and protecting privacy. Aiming at the problem that existing user attribute inference methods needs to make strong assumptions on the value of user attributes, an iterative method for user sensitive attributes in social network is proposed by combining the RL iterative classification framework and extending the wvRN relation inference method. Extracting probabilities of user sensitive attributes based on user text and convolution neural network and iteratively updating inference results with neighboring nodes, not only weakens the assumption of user attributes, but also improves the degree of application. The experimental results show that by obtaining a small amount of labeled data in social networks and setting reasonable parameter values for iterative inference methods, better user sensitive attribute inference results can be obtained.

Key words: social network, text classification, social link, attribute inference, data mining

CLC Number: 

  • TP309.2

Fig.1

Iterative inference process"

Fig.2

An example of TextCNN structure"

Table 1

Dataset division details"

标注率 训练集用户数 测试集用户数
0.1 3 220 28 983
0.2 6 440 25 763
0.3 9 660 22 543
0.4 12 881 19 322
0.5 16 101 16 102
0.6 22 542 9 661
0.7 22 542 9 661
0.8 25 762 6 441
0.9 28 982 3 221

Fig.3

Gender inference accuracy"

Fig.4

Province inference accuracy"

Fig.5

City inference accuracy"

1 ACQUISTI A, GROSS R. Imagined communities: awareness, information sharing, and privacy on the facebook[M]// ACQUISTI A, GROSS R. eds. Privacy Enhancing Technologies. Berlin: Springer, 2006: 36-58.
2 LI Xiaoxue, CAO Yannan, SHANG Yanmin, et al. Inferring user profiles in online social networks based on convolutional neural network[C]// Proceedings of International Conference on Knowledge Science, Engineering and Management(KSEM). New York: Springer, 2017: 274-286.
3 XU W H, ZHOU X, LI L. Inferring privacy information via social relations[C]//2008 IEEE 24th International Conference on Data Engineering Workshop. Mexico: ICDE, 2008: 525-530.
4 LINDAMOOD J, HEATHERLY R, KANTARCIOGLU M, et al. Inferring private information using social network data[C]// International Conference on World Wide Web. New York: ACM, 2008.
5 JIA Jinyuan, WANG Binghui, ZHANG Le, et al. AttriInfer: inferring user attributes in online social networks using Markov random fields[C]// Proceedings of International World Wide Web Conferences(WWW). New York: ACM, 2017: 1561-1569.
6 DONG Y X, TANG J, WU S, et al. Link prediction and recommendation across heterogeneous social networks[C]// IEEE International Conference on Data Mining. New York: IEEE, 2013.
7 CHAUDHARI G, AVADHANULA V, SARAWAGI S. A few good predictions: selective node labeling in a social network[C]// ACM International Conference on Web Search & Data Mining.[s.l.]: ACM, 2014.
8 ELENA Z, LISE G. To join or not to join: the illusion of privacy in social networks with mixed public and private user profiles[C]// Proceedings of International World Wide Web Conferences(WWW). New York: ACM, 2009: 531-540.
9 LARS B, ERIC S, CAMERON M. Find me if you can: improving geographical prediction with social and spatial proximity[C] // Proceedings of International World Wide Web Conferences(WWW). North Carolina: ACM, 2010: 61-70.
10 LI Rui, WANG Chi, CHANG Chenchuan. User profiling in an ego network: co-profiling attributes and relationships[C]// Proceedings of International World Wide Web Conferences(WWW). New Youk: ACM, 2014: 819-830.
11 DOUGNON R Y , FOURNIER-VIGER P , LIN J C W , et al. Inferring social network user profiles using a partial social graph[J]. Journal of Intelligent Information Systems, 2016, 47 (2): 313- 344.
doi: 10.1007/s10844-016-0402-y
12 WONG R K, VIDYALAKSHMI B S. Privacy leakage via attribute inference in directed social networks[C]// Proceedings of International Conference on Information and Communications Security(ICICS). Berlin: Springer. 2016: 333-346.
13 胡开先, 梁英, 许洪波, 等. 一种社会网络用户身份特征识别方法[J]. 计算机研究与发展, 2016, 53 (11): 2630- 2644.
doi: 10.7544/issn1000-1239.2016.20150219
HU Kaixian , LIANG Yin , XU Hongbo , et al. A method for social network user identity feature recognition[J]. Journal of Computer Research and Development, 2016, 53 (11): 2630- 2644.
doi: 10.7544/issn1000-1239.2016.20150219
14 GONG Zhenqiang, LIU Bin. You are who you know and how you behave: attribute inference attacks via users' social friends and behaviors[J]. arXiv: 1606.05893. https: //arxiv.org/abs/1606.05893
15 ABDELBERI C, GERGELY A, MOHAMED A K. You are what you like! Information leakage through users' interests[C]// Proceedings of ISOC Network and Distributed System Security Symposium(NDSS). San Diego: [s.n.], 2012.
16 ALAN M, BIMAL V, KRISHNA P, et al. You are who you know: inferring user profiles in online social networks[C]// Proceedings of ACM International Conference on Web Search and Data Mining(WSDM). New York: ACM, 2010: 251-260.
17 MACSKASSY S A , PROVOST F . Classification in networked data: a toolkit and a univariate case study[J]. Journal of Machine Learning Research, 2007, 8 (3): 1- 41.
18 YOON K. Convolutional neural networks for sentence classification[C] // Proceedings of Conference on Empirical Methods in Natural Language Processing(EMNLP). Doha: ACL, 2014: 1746-1751.
[1] SUI Yun-xian, LIU Yong. Mining algorithm of E-burt structural hole based on two-step neighbor [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2017, 52(9): 59-68.
[2] ZHANG Zhong-jun, ZHANG Wen-juan, YU Lai-hang, LI Run-chuan. A community division method based on network distance and content similarity in micro-blog social network [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2017, 52(7): 97-103.
[3] KANG Hai-yan, MA Yue-lei. Survey on application of data mining via differential privacy [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2017, 52(3): 16-23.
[4] DENG Xiao-fang, ZHONG Yuan-sheng, L(¨overU)Lin-yuan, WANG Ming-wen, XIONG Nai-xue. Mass diffusion on coupled social networks [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2017, 52(3): 51-59.
[5] LIU Xin, XU Qiu-liang, ZHANG Bo. Cooperative group signature scheme with controllable linkability [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(9): 18-35.
[6] ZHU Sheng, ZHOU Bin, ZHU Xiang. EIP: discovering influential bloggers by user similarity and topic timeliness [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(9): 113-120.
[7] GUO Hua-long, REN Xue-fang, ZHANG Ling. Relationships between dynamic data mining and P-augmented matrix [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(8): 105-110.
[8] CAI Hong-yun, MA Xiao-xue. Access control based on relationship strength for online social network [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(7): 90-97.
[9] WAN Zhong-ying, WANG Ming-wen, ZUO Jia-li, WAN Jian-yi. Feature selection combined with the global and local information(GLFS) [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(5): 87-93.
[10] REN Xue-fang, ZHANG Ling. Perturbation theorems of inverse P-sets and perturbation-based data mining [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(12): 54-60.
[11] ZHANG Shao-qun, WEI Jing-jing, LIAO Xiang-wen, JIAN Si-yuan, CHEN Guo-long. Emotional contagion in Twitter [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(1): 71-76.
[12] ZHANG Ling, REN Xue-fang. Surplus-deficient theorem of cardinal number and data internal-outer mining-separation [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2015, 50(08): 90-94.
[13] MA Cheng-long, JIANG Ya-song, LI Yan-ling, ZHANG Yan, YAN Yong-hong. Short text classification based on word embedding similarity [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(12): 18-22.
[14] ZHENG Yan, PANG Lin, BI Hui, LIU Wei, CHENG Gong. Feature selection algorithm based on sentiment topic model [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(11): 74-81.
[15] LI Qi1,2, MA Jun1,2*. Person′s name disambiguation based on person  related social communities [J]. J4, 2012, 47(3): 33-37.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] YANG Yong-wei1, 2, HE Peng-fei2, LI Yi-jun2,3. On strict filters of BL-algebras#br#[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(03): 63 -67 .
[2] PEI Sheng-yu，ZHOU Yong-quan. A mult-objective particle swarm optimization algorithm based on  the  chaotic mutation[J]. J4, 2010, 45(7): 18 -23 .
[3] DU Ji-xiang1,2, YU Qing1, ZHAI Chuan-ming1. Age estimation of facial images based on non-negative matrix factorization with sparseness constraints[J]. J4, 2010, 45(7): 65 -69 .
[4] XUE Qiu-fang1,2, GAO Xing-bao1*, LIU Xiao-guang1. Several equivalent conditions for H-matrix based on the extrapolated GaussSeidel iterative method[J]. J4, 2013, 48(4): 65 -71 .
[5] WANG Bing . Properties of a quasi-claw-free graph[J]. J4, 2007, 42(10): 111 -113 .
[6] . [J]. J4, 2009, 44(3): 84 -87 .
[7] WANG Qi,ZHAO Hong-luan . [J]. J4, 2006, 41(6): 84 -86 .
[8] QU Shouning, FU Aifang, LI Jing, LIU Jing. Forecasting stock market risks based on the flexible neural tree[J]. J4, 2009, 44(11): 44 -47 .
[9] SHAO Guo-jun, RU Miao-yan*, SUN Xue-ying. Study on synthesis process of polyether grafted polycarboxylate based superplasticizer[J]. J4, 2013, 48(05): 29 -33 .
[10] LIU Kun-lun. Application of variable structure pair copula model in the analysis of financial contagion[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(6): 104 -110 .
Copyright 2018 © Editorial office of JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)
Supported by Beijing Magtech Co.Ltd