Unsupervised Clustering-based SPITters Detection Scheme

Abstract

VoIP/SIP is taking place of conventional telephony because of very low call charge but it is also attractive for SPITters who advertise or spread phishing calls toward many callees. Although there exist many feature-based SPIT detection methods, none of them provides the flexibility against multiple features and thus complex threshold settings and training phases cannot be avoided. In this paper, we propose an unsupervised and threshold-free SPITters detection scheme based on a clustering algorithm. Our scheme does not use multiple features directly to trap SPITters but uses them to find the dissimilarity among each caller pair and tries to separate the callers into a SPITters cluster and a legitimate one based on the dissimilarity. By computer simulation, we show that the combination of Random Forests dissimilarity and PAM clustering brings the best classification accuracy and our scheme works well when the SPITters account for more than 20% of the entire caller.

Detection and prevention of spam over Internet telephony in Voice over Internet Protocol networks using Markov chain with incremental SVM

“…Owing to the exponential growth of the spam calls, researchers have paved various ways for mitigating the SPIT calls using various techniques such as policy based, turing test based, reputation based, payment at risk, Completely Automated Public Turing test to tell the Computers and Humans Apart (CAPTCHA), machine learning algorithms based and content based over the period of 2006 to 2015 …”

“…These methods extract appropriate features from both legitimate and spam callers and store them in a training set. Then, the training set is applied to machine learning algorithms in association with a test set to classify the unknown class using pre‐defined set of rules . However, some of the spammers are judged as legitimate user because of the misclassification nature of the machine learning algorithms.…”