Classification of encrypted traffic using deep learning

Abstract: In this paper we examine and evaluate different ways of classifying encrypted network traffic using neural networks. For this purposes we create a dataset with a streaming/non-streaming focus. The dataset comprises seven different classes, five streaming and two non-streaming. The thesis serves as a preliminary proof-of-concept for Napatech A/S. The most desirable approach for Napatech is to classify individual packets upon arrival. Our experiments show that this approach is infeasible due to the content being encrypted and therefore without any distinguishable information. We therefore propose a novel approach where the unencrypted parts of network traffic, namely the headers are utilized. This is done by concatenating the initial headers from a session thus forming a signature datapoint. In experiments using the header-based approach we achieve very promising results, showing that a simple neural network with a single hidden ii layer of less than 50 units, can predict the individual classes with an accuracy of 96.4% and an AUC of 0.99 to 1.00 for the individual classes. The thesis hereby provides a solution to network traffic classification using the unencrypted headers Keywords: Deep Learning, Encrypted Traffic, PCA, t-SNE, Neuron Network. Title: Classification of encrypted traffic using deep learning Author: Kausar Mia, Md. Tamjeed Monshi, Ms. Shanta Rani Saha, Sonjoy Prosad Shaha, Arnab Saha, Angkur Dhar, Md. Tasnim Forhad Rimon, Sadid mahamud International Journal of Computer Science and Information Technology Research ISSN 2348-1196 (print), ISSN 2348-120X (online) Vol. 11, Issue 1, January 2023 - March 2023 Page No: 52-67 Research Publish Journals Website: www.researchpublish.com Published Date: 19-February-2023 DOI: https://doi.org/10.5281/zenodo.7654314 Paper Download Link (Source) https://www.researchpublish.com/papers/classification-of-encrypted-traffic-using-deep-learning-International Journal of Computer Science and Information Technology Research, ISSN 2348-1196 (print), ISSN 2348-120X (online), Research Publish Journals, Website: www.researchpublish.co