社交网络用户敏感属性迭代识别方法
|
摘要
分析识别社交网络用户敏感信息,有利于从技术上量化隐私泄露程度,进行隐私保护。针对现有的用户属性识别方法需要对用户属性取值进行强假设的问题,结合RL迭代分类框架和扩展wvRN关系识别的方法,提出了一种社交网络用户敏感属性迭代识别方法。通过卷积神经网络提取用户文本特征进行识别,结合邻居结点迭代地进行关系识别,不仅弱化了对用户属性的假设,而且提高了可用性。实验结果表明,通过在社交网络中获取少量的标注数据,对迭代识别方法设置合理的参数值,可以获得较好的用户敏感属性识别结果。
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.
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.
引文
[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.
[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.HU Kaixian, LIANG Yin, XU Hongbo, el al. A method for social network user identity feature recognition [J]. Journal of Computer Research and Development, 2016, 53(11): 2630-2644.
[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.
[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.
[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.HU Kaixian, LIANG Yin, XU Hongbo, el al. A method for social network user identity feature recognition [J]. Journal of Computer Research and Development, 2016, 53(11): 2630-2644.
[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.