TW-FCM: An Improved Fuzzy-C-Means Algorithm for SPIT Detection

With the popularity of VoIP (Voice over Internet Protocol) systems, there has been an explosive growth in VoIP spam. In order to effectively prevent spam calls, various methods based on the analysis of call behavior features have been proposed. However, few of the existing methods consider that different features have different weights, resulting in a low detection precision of SPIT (Spam over Internet Telephony) users. Meanwhile, most methods are tested based on the experimental data generated by simulation, it is not sure whether these methods work well in the real world. In this paper, we propose a Weighted-Fuzzy-C-Means (W- FCM) algorithm, which can automatically adjust the weight of each call feature in the clustering process. Experiments based on the real world data show that our proposed algorithm could effectively improve the detection precision (about 6.7%) and recall (about 0.3%) of SPIT users. We also analyze the impact of different membership thresholds on the clustering results and propose a Threshold-W-FCM (TW-FCM) algorithm, through which we can select appropriate membership thresholds to alleviate the class-imbalance problem, and thereby improve the overall performance of SPIT detection compared with traditional FCM method.

[1]  Wenyuan Xu,et al.  You Can Call but You Can't Hide: Detecting Caller ID Spoofing Attacks , 2014, 2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks.

[2]  Neil W. Bergmann,et al.  VoIP Spam Prevention , 2013, 2013 12th IEEE International Conference on Trust, Security and Privacy in Computing and Communications.

[3]  Saurabh Bagchi,et al.  Spam detection in voice-over-IP calls through semi-supervised clustering , 2009, 2009 IEEE/IFIP International Conference on Dependable Systems & Networks.

[4]  Muhammad Ajmal Azad,et al.  Mitigating SPIT with Social Strength , 2012, 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications.

[5]  Xiao Su,et al.  Detection and filtering Spam over Internet Telephony — a user-behavior-aware intermediate-network-based approach , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[6]  Christoph Sorge,et al.  A Provider-Level Reputation System for Assessing the Quality of SPIT Mitigation Algorithms , 2009, 2009 IEEE International Conference on Communications.

[7]  Panagiotis Galiotos,et al.  Non-conforming behavior detection for VoIP-based network systems , 2016, 2016 IEEE International Conference on Communications (ICC).

[8]  Xiao Su,et al.  Adaptive Voice Spam Control with User Behavior Analysis , 2009, 2009 11th IEEE International Conference on High Performance Computing and Communications.

[9]  Heiko Knospe,et al.  An efficient search method for the content-based identification of telephone-SPAM , 2012, 2012 IEEE International Conference on Communications (ICC).

[10]  Mark Handley,et al.  SIP: Session Initiation Protocol , 1999, RFC.

[11]  Tomoaki Ohtsuki,et al.  Novel Unsupervised SPITters Detection Scheme by Automatically Solving Unbalanced Situation , 2017, IEEE Access.

[12]  Adel Bouhoula,et al.  Behavior-based approach to detect spam over IP telephony attacks , 2015, International Journal of Information Security.

[13]  Adam Doupé,et al.  SoK: Everyone Hates Robocalls: A Survey of Techniques Against Telephone Spam , 2016, 2016 IEEE Symposium on Security and Privacy (SP).

[14]  Dimitris Gritzalis,et al.  A game-theoretic analysis of preventing spam over Internet Telephony via audio CAPTCHA-based authentication , 2014, J. Comput. Secur..

[15]  Enrique H. Ruspini,et al.  A New Approach to Clustering , 1969, Inf. Control..

[16]  Xinyuan Wang,et al.  Call Behavioral Analysis to Thwart SPIT Attacks on VoIP Networks , 2011, SecureComm.

[17]  Michael K. Ng,et al.  Automated variable weighting in k-means type clustering , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Wenyuan Xu,et al.  End-to-End Detection of Caller ID Spoofing Attacks , 2018, IEEE Transactions on Dependable and Secure Computing.

[19]  Antonio Nucci,et al.  You can SPIT, but you can't hide: Spammer identification in telephony networks , 2011, 2011 Proceedings IEEE INFOCOM.

[20]  Vennila Ganesan,et al.  Dynamic voice spammers detection using Hidden Markov Model for Voice over Internet Protocol network , 2018, Comput. Secur..

[21]  Feiping Nie,et al.  Robust and Sparse Fuzzy K-Means Clustering , 2016, IJCAI.

[22]  Seungjoo Kim,et al.  VoIP-aware network attack detection based on statistics and behavior of SIP traffic , 2015, Peer Peer Netw. Appl..

[23]  Alessandro Laio,et al.  Clustering by fast search and find of density peaks , 2014, Science.

[24]  Iwao Sasase,et al.  SPIT callers detection with unsupervised Random Forests classifier , 2013, 2013 IEEE International Conference on Communications (ICC).

[25]  Benxiong Huang,et al.  ADVS: a reputation-based model on filtering SPIT over P2P-VoIP networks , 2010, The Journal of Supercomputing.

[26]  Muhammad Ali Akbar,et al.  Securing SIP-based VoIP infrastructure against flooding attacks and Spam Over IP Telephony , 2012, Knowledge and Information Systems.