Classification of Virtual Private networks encrypted traffic using ensemble learning algorithms

Almomani, A (2022) Classification of Virtual Private networks encrypted traffic using ensemble learning algorithms. Egyptian Informatics Journal. ISSN 1110-8665

[thumbnail of Classification of vitual.pdf] Text
Classification of vitual.pdf - Published Version

Download (2MB)

Abstract

Virtual Private Networks (VPNs) are one example of encrypted communication services commonly used to bypass censorship and access geographically locked services. This study performed VPN and non-VPN traffic analysis and developed a classification system based on the new techniques of machine learning classifiers known as stacking ensemble learning. The methods used for VPN and Non-VPN classification use three machine learning techniques: random forest, neural network, and support vector machine. To assess the proposed method's performance, we tested it on a dataset containing 61 features. The experiment results accurately prove the study's classifiers to differentiate between VPN and Non-VPN traffic. The accuracy level was approximately 99% in the training and testing phase. The study's classifiers also show the best standard deviation, with a 100% accuracy rate compared to other A.I. classifier methods.

Affiliation: Skyline University College
SUC Author(s): Almomani, A ORCID: https://orcid.org/0000-0002-8808-6114
All Author(s): Almomani, A
Item Type: Article
Uncontrolled Keywords: Ensemble Learning, Machine learning, (VPN (and Non-VPN traffic analysis, Encrypted traffic
Subjects: B Information Technology > BR Deep Learning
Divisions: Skyline University College > School of IT
Depositing User: Mr Veeramani Rasu
Date Deposited: 09 Aug 2022 06:23
Last Modified: 09 Aug 2022 06:23
URI: https://research.skylineuniversity.ac.ae/id/eprint/562
Publisher URL: https://doi.org/10.1016/j.eij.2022.06.006
Publisher OA policy: https://v2.sherpa.ac.uk/id/publication/17760
Related URLs:

Actions (login required)

View Item
View Item
Statistics for SkyRep ePrint 562 Statistics for this ePrint Item