The Impact of Evasion on the Generalization of Machine Learning Algorithms to Classify VoIP Traffic

We propose a novel approach to generate well generalized signatures to classify Skype VoIP traffic using a machine learning based approach. Results show that the performance of the signatures did not degrade significantly when they were evaluated on traffic that was captured from different locations and at different times as well as employed against evasion attacks. Our results on the evasion of Skype classifier demonstrate that the performance of the signatures are very promising even if the user tries maliciously to alter the characteristics of Skype traffic to evade the classifier.