DeepFriend: finding abnormal nodes in online social networks using dynamic deep learning

Wanda P., Jie H.J.

Harbin University of Science and Technology, Harbin, China; Universitas Respati Yogyakarta, Yogyakarta, Indonesia


Abstract

Detection of Online Social Networks (OSN) anomalous nodes becomes increasingly essential to identify malicious activities. The abnormal nodes suspiciously construct improbable links to other benign accounts. Inspired by the significant achievements of deep learning in current computer vision problems, we propose DeepFriend as a novel supervised neural network to classify abnormal nodes using labeled link features dataset. This paper proposes a model to classify malicious vertices using nodes’ link information by training extensive features with dynamic deep learning architecture. To construct dynamic deep learning, we present a generic function called WalkPool pooling to optimize our network performance. By demonstrating our model, we gain higher accuracy than standard learning algorithms in the abnormal nodes’ classification. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.

Abnormal nodes; Deep learning; Online social network; Social relation


Journal

Social Network Analysis and Mining

Publisher: Springer

Volume 11, Issue 1, Art No 34, Page – , Page Count


Journal Link: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103264189&doi=10.1007%2fs13278-021-00742-2&partnerID=40&md5=244fb02aade5bc7802210471d0ab68e6

doi: 10.1007/s13278-021-00742-2

Issn: 18695450

Type:


References

Abeer, A.-M., Maha, H., Nada, A.-S., Hemalatha, M., Security issues in social networking sites (2016) Int J Appl Eng Res, 11-12, pp. 7672-7675; Adamic, L.A., Adar, E., How to search a social network (2005) Soc Netw, 27 (3), pp. 187-203; Ahmad, I., (2015) How Many Internet and #Socialmedia Users are Fake?, , http://www.digitalinformationworld.com/2015/04/infographic-how-many-internetsusers-are-fake.html, Avalaible; Ahmed, N.M., Chen, L., An efficient algorithm for link prediction in temporal uncertain social networks (2016) Inf Sci, 331, pp. 120-136; Al-Qurishi, M., Al-Rakhami, M., Alamri, A., Alrubaian, M., Rahman, S.M.M., Hossain, M.S., Sybil defense techniques in online social networks: a survey (2017) IEEE Access, 5, pp. 1200-1219; Anglano, C., Canonico, M., Guazzone, M., Analysis of telegram messenger on android smartphones (2017) Digit Investig, 23, pp. 31-49; Barabási, A.-L., Jeong, H., Néda, Z., Ravasz, E., Schubert, A., Vicsek, T., Evolution of the social network of scientific collaborations (2002) Phys A Stat Mech Appl, 311 (3), pp. 590-614; Bindu, P., Thilagam, S., Mining social networks for anomalies: Methods and challenges (2016) J Netw Comput Appl, 68, pp. 213-229; Bliss, C.A., Frank, M.R., Danforth, C.M., Dodds, P.S., An evolutionary algorithm approach to link prediction in dynamic social networks (2014) J Comput Sci, 5 (5), pp. 750-764; Boccaletti, S., Latora, V., Moreno, Y., Chavez, M., Hwang, D.U., Complex networks: structure and dynamics (2006) Phys Rep, 424 (4-5), pp. 175-308; Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P., SMOTE: synthetic minority over-sampling technique (2002) J Artif Intell Res, 16, pp. 321-357; Chiu, C., Zhan, J., Deep learning for link prediction in dynamic networks using weak estimators (2018) IEEE Access, 6, pp. 35937-35945; (2018) Facebook Says Data on 87 Million People May have Been Shared in Cambridge Analytica Leak., , https://www.forbes.com/sites/kathleenchaykowski/2018/04/04/facebook-says-data-on-87-million-people-may-have-beenshared-in-cambridge-analytica-leak/#484f39eb3e8b, Avalaible; Gong, Q., DeepScan: exploiting deep learning for malicious account detection in location-based social networks (2018) IEEE Commun Mag, 56 (11), pp. 21-27; Deep learning (2016) Books, p. 184; Grover, A., Leskovec, J., Node2vec: Scalable feature learning for networks (2016) Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Jiang, J., Anomaly detection with graph convolutional networks for insider threat and fraud detection (2019) MILCOM 2019—2019 IEEE Military Communications Conference (MILCOM), Norfolk, VA, USA, pp. 109-114. , https://doi.org/10.1109/MILCOM47813.2019; Jie, H.J., Wanda, P., RunPool: a dynamic pooling layer for convolution neural network (2020) Int J Comput Intell Syst, 13 (1), pp. 66-76; Kalchbrenner, N., Grefenstette, E., Blunsom, P., A convolutional neural network for modelling sentences (2014) Proceedings of the 52Nd Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics; Katz, L., A new status index derived from sociometric analysis (1953) Psychometrika, 18 (1), pp. 39-43; Kipf, T., Welling, M., Semi-supervised classification with graph convolutional networks (2017) Arxiv, Abs/1609.02907; Kökciyan, N., Yolum, P., ProGuard: a semantic approach to detect privacy violations in online social networks (2016) IEEE Trans Knowl Data Eng, 28 (10), pp. 2724-2737; LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition (1998) Proc IEEE, 86 (11), pp. 2278-2324; LeCun, Y., Bengio, Y., Hinton, G., Deep learning (2015) Nature, 521, pp. 436-444; Lin, L., Xu, L., Zhou, S., Wu, W., The social feature-based priority relation graph of mobile social networks (2014) 2014 IEEE 17Th International Conference on Computational Science and Engineering, pp. 1921-1926. , Chengdu; Liu, B.-H., Hsu, Y.-P., Ke, W.-C., Virus infection control in online social networks based on probabilistic communities (2014) Int J Commun Syst, 27, pp. 4481-4491; Liu, F., Liu, B., Sun, C., Liu, M., Wang, X., Deep belief network-based approaches for link prediction in signed social networks (2015) Entropy, 17 (4), pp. 2140-2169; Liu, Z., Li, S., Zhang, Y., Yun, X., Peng, C., Ringer: Systematic mining of malicious domains by dynamic graph convolutional network (2020) Computational Science—ICCS 2020: 20Th International Conference, Amsterdam, the Netherlands, June, 3-5, p. 2020; Li, T., Wang, B., Jiang, Y., Zhang, Y., Yan, Y., Restricted Boltzmann machine-based approaches for link prediction in dynamic networks (2018) IEEE Access, 6, pp. 29940-29951; Li, X., Xin, Y., Zhao, C., Yang, Y., Chen, Y., Graph convolutional networks for privacy metrics in online social networks (2020) Appl Sci, 10, p. 1327; Looks, M., Herreshoff, M., Hutchins, D., Norvig, P., Deep learning with dynamic computation graphs (2017) ICLR Conference; Marcelo, L., Issa, T., Isaac, W., Mohammad, S., Authorship verification using deep belief network system (2017) Int J Commun Syst; Mohammadrezaei, M., Shiri, M.E., Rahmani, A.M., Identifying fake accounts on social networks based on graph analysis and classification algorithms (2018) Hindawi Security Commun Netw; Newman, M.E.J., Clustering and preferential attachment in growing networks (2001) Phys Rev E Stat Phys Plasmas Fluids Relat Interdiscip Top, 64 (2), p. 025102; Nurse, J.R.C., Erola, A., Goldsmith, M., Creese, S., Investigating the leakage of sensitive personal and organizational information in email headers (2015) J Internet Services Inf Secur (JISIS), 5, pp. 70-84; Perozzi, B., Al-Rfou, R., Skiena, S., DeepWalk: Online learning of social representations (2014) KDD ’14; Qin, Y., Jia, R., Zhang, J., Wu, W., Wang, X., Impact of social relation and group size in multicast ad hoc networks (2016) IEEE/ACM Trans Netw, 24 (4), pp. 1989-2004; Savage, D., Zhang, X., Yu, X., Chou, P., Wang, Q., Anomaly detection in online social networks (2014) Social Netw, 39, pp. 62-70; Sharma, V., You, I., Kumar, R., ISMA: intelligent sensing model for anomalies detection in cross-platform OSNs with a case study on IoT (2017) IEEE Access, 5, pp. 3284-3301; Sohrabi, M.K., Karimi, F., A feature selection approach to detect spam in the facebook social network (2018) Arab J Sci Eng, 43 (2), pp. 949-958; Taigman, Y., Yang, M., Ranzato, M., Wolf, L., Deepface: closing the gap to human-level performance in face verification (2014) Computer Vision and Pattern Recognition (CVPR), IEEE Conference on Pattern Recognition, pp. 1701-1708; Theodoridis, S., Pikrakis, A., Koutroumbas, K., Cavouras, D., (2010) Introduction to pattern recognition: a MATLAB approach, , Academic, San Diego, CA, USA; Vigliotti, M.G., Hankin, C., Discovery of anomalous behaviour in temporal networks (2015) Social Netw, 41, pp. 18-22; Wanda, P., Jie, H.J., DeepProfile: finding fake profile in online social network using dynamic CNN (2020) J Inf Secur Appl, 52, p. 102465; Wanda, P., Marselina Endah, H., Jie, H.J., DeepOSN: Bringing deep learning as malicious detection scheme in online social network (2020) IAES Int J Artif Intell (IJ-AI), 9 (1), p. 146; Wang, P., Xu, B., Wu, Y., Zhou, X., Link prediction in social networks: The state-of-the-art (2015) Sci China Inf Sci, 58 (1), pp. 1-38; Zhou, F., Liu, L., Zhang, K., Trajcevski, G., Wu, J., Zhong, T., DeepLink: A deep learning approach for user identity linkage (2018) IEEE INFOCOM 2018—IEEE Conference on Computer Communications, pp. 1313-1321. , Honolulu, HI

Indexed by Scopus

Leave a Comment