Computer Science ›› 2020, Vol. 47 ›› Issue (2): 251-255.doi: 10.11896/jsjkx.190600172

• Information Security • Previous Articles     Next Articles

Fake Account Detection Method in Online Social Network Based on Improved Edge Weighted Paired Markov Random Field Model

SONG Chang,YU Ke,WU Xiao-fei   

  1. (School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China)
  • Received:2019-06-28 Online:2020-02-15 Published:2020-03-18
  • About author:SONG Chang,born in 1995,postgra-duate.Her main research interests include online social network analysis and data mining;YU Ke,born in 1977,Ph.D,associate professor.Her main research interests include communication network theory,network data mining,mobile Internet application,machine learning and human-machine intelligence.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61601046, 61171098), 111 Project of China (B08004) and EU FP7 IRSES Mobile Cloud Project (612212).

Abstract: Social media systems provide a convenient platform for sharing,communication and collaboration.When people enjoy the openness and convenience of social media,there may be many malicious acts,such as bullying,terrorist attacks and fraudulent information dissemination.Therefore,it is very important to be able to detect these anomalous activities as accurately and early as possible to prevent disasters and attacks.The success of online social networks (OSN) in recent years,such as Twitter,Facebook,Google+,LinkedIn,has made them targests of attacker’s goal due to their rich profit resources.The openness of social networks makes them particularly vulnerable to unusual account attacks.Existing classification models mostly use method that first assign weights to the edges of the graph,iteratively propagate the reputation scores of the nodes in the weighted graph,and use the final posterior scores to classify the nodes.One of the important tasks is the settingof edge weight.This parameter will directly affect the accuracy of the test results.Based on the detection task of fake account in social media,this paper analyzed the global structure based on social graph,and improves the algorithm of edge weight in the paired Markov random field model,so that it can adaptively optimize in the iterative process.GANG+LW,GANG+LOGW,and GANG+PLOGW algorithms with higher accuracy were proposed.These three algorithms used three different methods to improve the algorithm of edge weight.Experiments show that the proposed method can obtain more accurate fake account detection results than the basic paired Markov random field model,in which GANG+PLOGW got the best results in the three algorithms.The result proves that this improved model can solve the problem more effectively when detecting fake accounts in social networks.

Key words: Fake account detection, Markov random field, Social media, Sybil attack

CLC Number: 

  • TP181
[1]YU R,QIU H D,WEN Z,et al.A Survey on Social Media Anomaly Detection[J].ACM SIGKDD Explorations Newsletter,2016,18(1):1-4.
[2]GAO P,WANG B,GONG N Z,et al.Sybilfuse:Combining local attributes with global structure to perform robust sybil detection[J].arXiv:1803.06772,2018.
[3]YANG Z,XUE J,YANG X,et al.VoteTrust:Leveraging friend invitation graph to defend against social network sybils[J].IEEE Transactions on Dependable and Secure Computing,2016,13(4):488-501.
[4]MISRA S,TAYEEN A S M,XU W.SybilExposer:An effective scheme to detect Sybil communities in online social networks[C]∥2016 IEEE International Conference on Communications (ICC).IEEE,2016:1-6.
[5]ZHENG H,XUE M,LU H,et al.Smoke screener or straight shooter:Detecting elite sybil attacks in user-review social networks[J].arXiv:1709.06916,2017.
[6]DAVIS C A,VAROL O,FERRARA E,et al.BotOrNot:A system to evaluate social bots[C]∥Proceedings of the 25th International Conference Companion on World Wide Web.International World Wide Web Conferences Steering Committee,2016:273-274.
[7]SAVAGE D,ZHANG X Z,YU X H,et al.Anomaly Detection in Online Social Network[J].Social Network,2014,39:62-70.
[8]YANG Z,WILSON C,WANG X,et al.Uncovering social network sybils in the wild[J].ACM Transactions on Knowledge Discovery from Data (TKDD),2014,8(1):2.
[9]GATTERBAUER W,GÜNNEMANN S,KOUTRA D,et al. Linearized and single-pass belief propagation[J].Proceedings of the VLDB Endowment,2015,8(5):581-592.
[10]LIU Y,CHAWLA S.Social media anomaly detection:Challenges and solutions[C]∥Proceedings of the Tenth ACM International Conference on Web Search and Data Mining.ACM,2017:817-818.
[11]BIMAL V,BASHIR M A,MARK C,et al.Towards Detecting Anomalous User Behavior in Online Social Networks[M]∥Lecture Notes in Computer Science.Berlin:Springer,2014:223-238.
[12]GONG N Z,FRANK M,MITTAL P.SybilBelief:A semi-supervised learning approach for structure-based sybil detection[J].IEEE Transactions on Information Forensics and Security,2014,9(6):976-987.
[13]GAO P,GONG N Z,KULKARNI S,et al.Sybilframe:A de-fense-in-depth framework for structure-based sybil detection[J].arXiv:1503.02985,2015.
[14]WANG B,ZHANG L,GONG N Z.SybilBlind:Detecting Fake Users in Online Social Networks without Manual Labels[J].arXiv:1806.04853,2018.
[15]WANG B,JIA J,GONG N Z.Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation[J].arXiv:1812.01661,2018.
[16]WANG B,GONG N Z,FU H.GANG:Detecting fraudulent users in online social networks via guilt-by-association on directed graphs[C]∥2017 IEEE International Conference on Data Mi-ning (ICDM).IEEE,2017:465-474.
[17]WANG B,ZHANG L,GONG N Z.SybilSCAR:Sybil detection in online social networks via local rule based propagation[C]∥2017 IEEE International Conference on Computer Communications.IEEE,2017.
[18]YANG C,HARKREADER R,ZHANG J L,et al.Analyzing Spammers’ Social Networks For Fun and Profit:A Case Study of Cyber Criminal Ecosystem on Twitter[C]∥Proceedings of the 21st International World Wide Web.New York:ACM,2012.
[1] ZHOU Xu, QIAN Sheng-sheng, LI Zhang-ming, FANG Quan, XU Chang-sheng. Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification [J]. Computer Science, 2022, 49(9): 132-138.
[2] WANG Jian, PENG Yu-qi, ZHAO Yu-fei, YANG Jian. Survey of Social Network Public Opinion Information Extraction Based on Deep Learning [J]. Computer Science, 2022, 49(8): 279-293.
[3] YAO Xiao-ming, DING Shi-chang, ZHAO Tao, HUANG Hong, LUO Jar-der, FU Xiao-ming. Big Data-driven Based Socioeconomic Status Analysis:A Survey [J]. Computer Science, 2022, 49(4): 80-87.
[4] DAI Hong-liang, ZHONG Guo-jin, YOU Zhi-ming , DAI Hong-ming. Public Opinion Sentiment Big Data Analysis Ensemble Method Based on Spark [J]. Computer Science, 2021, 48(9): 118-124.
[5] ZHANG Zhi-yang, ZHANG Feng-li, TAN Qi, WANG Rui-jin. Review of Information Cascade Prediction Methods Based on Deep Learning [J]. Computer Science, 2020, 47(7): 141-153.
[6] ZHANG Zhi-yang, ZHANG Feng-li, CHEN Xue-qin, WANG Rui-jin. Information Cascade Prediction Model Based on Hierarchical Attention [J]. Computer Science, 2020, 47(6): 201-209.
[7] LIN Min-hong, MENG Zu-qiang. Multimodal Sentiment Analysis Based on Attention Neural Network [J]. Computer Science, 2020, 47(11A): 508-514.
[8] LI Hai-xue, LIN Hai-tao, CHEN Jin. Self-adapting Regular Constraint Algorithm in Super-resolution of Single-frame Images [J]. Computer Science, 2019, 46(6A): 200-204.
[9] LIU Xiao, WANG Xiao-guo. Probabilistic Graphical Model Based Approach for Bank Telecommunication Fraud Detection [J]. Computer Science, 2018, 45(7): 122-128.
[10] YONG Tso, SHI Xiao-dong, NyimaTrashi. Research Status of Sentiment Analysis for Short Text
——From Social Media to Scarce Resource Language
[J]. Computer Science, 2018, 45(6A): 46-49.
[11] XU Cheng-hao, GUO Bin, OUYANG Yi, ZHAI Shu-ying and YU Zhi-wen. Event Sensing and Multimodal Event Vein Generation Leveraging Social Media [J]. Computer Science, 2017, 44(Z6): 33-36.
[12] ZHU Pei-song, QIAN Tie-yun and WU Min-quan. Identifying Users’ Gender via Social Representations [J]. Computer Science, 2017, 44(Z11): 160-165.
[13] ZHANG Yan-hong and WANG Bao-hui. Analysis of Social Media Networks Based on Deep Neural Networks [J]. Computer Science, 2016, 43(4): 252-255.
[14] KANG Kai, ZHANG Ying-jun, LIAN Yi-feng and LIU Yu-ling. Compound Approach for Sybil Users Detection in Social Networks [J]. Computer Science, 2016, 43(1): 172-177.
[15] LI Min, XIAO Sheng, LIU Zheng-jie and ZHANG Jun. Research on Field Influence of Digu Users [J]. Computer Science, 2015, 42(9): 66-69.
Full text



No Suggested Reading articles found!