Detection of Fake Accounts in Social Networks Based on One Class Classification

Document Type: ORIGINAL RESEARCH PAPER

Authors

1 Department of Computer, Borujerd Branch, Islamic Azad University, Borujerd, Iran

2 Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran

3 Computer engineering department, Science and Research Branch, Islamic Azad University, Tehran, Iran

Abstract

Detection of fake accounts on social networks is a challenging process. The previous methods in identification of fake accounts have not considered the strength of the users’ communications, hence reducing their efficiency. In this work, we are going to present a detection method based on the users’ similarities considering the network communications of the users. In the first step, similarity measures somethings such as common neighbors, common neighbors graph edges, cosine, and the Jaccard similarity coefficient are calculated based on adjacency matrix of the corresponding graph of the social network. In the next step, in order to reduce the complexity of data, Principal Component Analysis is applied to each computed similarity matrix to provide a set of informative features. then, a set of highly informative eigenvectors are selected using elbow-method. Extracted features are employed to train a One Class Classification (OCC) algorithm. Finally, this trained model is employed to identify fake accounts. As our experimental results indicate the promising performance of the proposed method a detection accuracy and false negative rates are 99.6% and 0%, respectively. We conclude that bringing similarity measures and One Class Classification algorithms into play, rather than the multi-class algorithms, provide better results.

Keywords


[1] Kagan, D., M. Fire, and Y. Elovici, Unsupervised Anomalous Vertices Detection Utilizing Link Prediction Algorithms. arXiv preprint arXiv:1610.07525, 2016.

[2] Domingo-Ferrer, J., et al., Privacy homomorphisms for social networks with private relationships. 2008. 52(15): p. 3007-3016.

[3] Gao, H., et al., Security issues in online social networks. 2011. 15(4): p. 56-63.

[4] Cutillo, L.A., R. Molva, and T.J.I.C.M. Strufe, Safebook: A privacy-preserving online social network leveraging on real-life trust. 2009. 47(12): p. 94-101.

[5] Van Eecke, P., M.J.C.L. Truyens, and S. Review, Privacy and social networks. 2010. 26(5): p. 535546.

[6] Adewole, K.S., et al., Malicious accounts: dark of the social networks. Journal of Network and Computer Applications, 2017. 79: p. 41-67.

[7] Krombholz, K., D. Merkl, and E. Weippl, Fake identities in social media: A case study on the sustainability of the facebook business model. Journal of Service Science Research, 2012. 4(2): p. 175-212.

[8] Yu, H., et al. Sybilguard: defending against sybil attacks via social networks. in ACM SIGCOMM Computer Communication Review. 2006. ACM.

[9] Subrahmanian, V., et al., The DARPA Twitter bot challenge. 2016.

[10] Van Der Walt, E. and J.J.I.A. Eloff, Using Machine Learning to Detect Fake Identities: Bots vs Humans. 2018. 6: p. 6540-6549.

[11] Fire, M., et al., Online social networks: threats and solutions. 2014. 16(4): p. 2019-2036. [12] Becker, J.L. and H. Chen, Measuring privacy risk in online social networks. 2009.

[13] Clifton, L.A. and D.S. Yin, Multi-channel novelty detection and classifier combination. 2007: University of Manchester.

[14] Dong, L., et al., The algorithm of link prediction on social network. Mathematical Problems in Engineering, 2013. 2013.

[15] Bank, J. and B.J.W.S.T. Cole, Calculating the jaccard similarity coefficient with map reduce for entity pairs in wikipedia. 2008: p. 1-18.

[16] Mohammadrezaei,M.,et al.,IdentifyingFakeAccounts on Social Networks Based on Graph Analysis and Classification Algorithms. 2018. 2018.

[17] Akcora, C.G., B. Carminati, and E. Ferrari, User similarities on social networks. Social Network Analysis and Mining, 2013. 3(3): p. 475-495.

[18] Santisteban, J. and J. Tejada-CÃąrcamo. Unilateral Jaccard Similarity Coefficient. in GSB@ SIGIR. 2015.

[19] Li, Q., et al. Mining user similarity based on location history. in Proceedings of the 16th ACM SIGSPATIAL international conference on Advances in geographic information systems. 2008. ACM.

[20] Bayardo, R.J., Y. Ma, and R. Srikant. Scaling up all pairs similarity search. in Proceedings of the 16th international conference on World Wide Web. 2007. ACM.

[21] Gionis, A., P. Indyk, and R. Motwani. Similarity search in high dimensions via hashing. in Vldb. 1999.

[22] Akcora, C.G., et al., User similarities on social networks. 2013. 3(3): p. 475-495.

[23] Bishop, C.M.J.P.r. and m. learning, Graphical models. 2006. 4: p. 359-422.

[24] Alpaydin, E., Introduction to machine learning. 2009: MIT press.

[25] Hempstalk, K., E. Frank, and I.H. Witten. Oneclass classification by combining density and class probability estimation. in Joint European Conference on Machine Learning and Knowledge Discovery in Databases. 2008. Springer.

[26] Khan, S.S. and M.G. Madden. A survey of recent trends in one class classification. in Irish conference on artificial intelligence and cognitive science. 2009. Springer.

[27] Amer, M., M. Goldstein, and S. Abdennadher. Enhancing one-class support vector machines for unsupervised anomaly detection. in Proceedings of the ACM SIGKDD Workshop on Outlier Detection and Description. 2013. ACM.

[28] SchÃűlkopf, B., et al. Support vector method for novelty detection. in Advances in neural information processing systems. 2000.

[29] Cao, J., et al., Discovering hidden suspicious accounts in online social networks. 2017. 394: p. 123-140.

[30] Wang, G., et al., Fine-grained feature-based

socialinfluenceevaluationinonlinesocialnetworks. 2014. 25(9): p. 2286-2296.

[31] Vigliotti, M.G. and C.J.S.N. Hankin, Discovery of anomalous behaviour in temporal networks. 2015. 41: p. 18-25.

[32] Al Hasan, M., et al. Link prediction using supervised learning. in SDM06: workshop on link analysis, counter-terrorism and security. 2006.

[33] Adewole, K.S., et al., Malicious accounts: dark of the social networks. 2017. 79: p. 41-67. [34] Savage, D., et al., Anomaly detection in online social networks. 2014. 39: p. 62-70.

[35] Zhang, Y., J.J.S.N.A. Lu, and Mining, Discover millions of fake followers in Weibo. 2016. 6(1): p. 16.
[36] Conti, M., R. Poovendran, and M. Secchiero. Fakebook: Detecting fake profiles in on-line social networks. in Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2012). 2012. IEEE Computer Society.

[37] Cao, J., et al., Detection of forwarding-based malicious URLs in online social networks. 2016. 44(1): p. 163-180.

[38] Boshmaf,Y.,et al.,ÃŊntegro:Leveragingvictim prediction for robust fake account detection in large scale OSNs. Computers & Security, 2016. 61: p. 142-168.

[39] Egele,M.,et al.,Towardsdetectingcompromised accounts on social networks. 2017(1): p. 1-1.

[40] Lee, S. and J.J.C.C. Kim, Early filtering of ephemeral malicious accounts on Twitter. 2014. 54: p. 48-57.

[41] Kiruthiga, S. and A. Kannan. Detecting cloning attack in Social Networks using classification and clustering techniques. in Recent Trends in Information Technology (ICRTIT), 2014 International Conference on. 2014. IEEE.

[42] Cao, Q., et al. Aiding the detection of fake accounts in large scale social online services. in Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation. 2012. USENIX Association.

[43] Kiselev, V.Y., et al., SC3: consensus clustering of single-cell RNA-seq data. 2017. 14(5): p. 483.

[44] Thorndike, R.L.J.P., Who belongs in the family? 1953. 18(4): p. 267-276.

[45] Pouyan, M.B. and D.J.b. Kostka, Random forest based similarity learning for single cell RNA sequencing data. 2018: p. 258699.

[46] Johnstone,I.M.andA.Y.J.a.p.a.Lu,Sparseprincipal components analysis. 2009.

[47] Heller, K., et al., One class support vector machines for detecting anomalous windows registry accesses. 2003.