Event Details

Dark Web Traffic Detection Using Supervised Machine Learning

Presenter: Sahra Zangeneh Nezhad
Supervisor:

Date: Thu, March 30, 2023
Time: 08:30:00 - 09:30:00
Place: via Zoom - please see link below

ABSTRACT

Zoom Meeting Link:
https://uvic.zoom.us/j/89319756841?pwd=cVJzVk5NZHZaQ0ZoZEY1U01ZS2dUZz09

Meeting ID: 893 1975 6841
Password: 037959
One tap mobile
+17789072071,,89319756841# Canada
+16475580588,,89319756841# Canada

Dial by your location
        +1 778 907 2071 Canada
        +1 647 558 0588 Canada
Meeting ID: 893 1975 6841
Find your local number: https://uvic.zoom.us/u/kA0gwc1nE

Note: Please log in to Zoom via SSO and your UVic Netlink ID

ABSTRACT:

The dark web, a hidden aspect of the internet that cannot be easily indexed by traditional search engines, is notorious for being a hub of illicit activities, including cybercrime, drug trafficking, and money laundering. The widespread use of anonymizing technologies, such as Virtual Private Networks (VPNs) and The Onion Router (TOR), has made it increasingly difficult for law enforcement agencies to identify and prosecute individuals engaged in such illegal activities. Thus, the accurate differentiation and categorization of VPN and TOR traffic on the dark web has become a critical challenge in the ongoing fight against cybercrime. To address this challenge, this study investigates the feasibility of utilizing machine learning algorithms to distinguish and categorize VPN and TOR traffic on the dark web. Specifically, the study utilizes the CIC-Darknet2020 dataset, which contains a diverse collection of network traffic captures from the dark web that incorporates traffic features from both VPN and TOR technologies. The study employs four classification algorithms - Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), and the Decision Tree (J48) classifiers - to construct a supervised machine learning model. The performance of the model is evaluated based on various parameters, including accuracy, precision, F-measure, recall, execution time, and different cross-validation techniques. The findings of this study demonstrate that the Decision Tree (J48) classifier outperforms the other classifiers in accurately distinguishing and categorizing VPN and TOR traffic on the dark web. The research has important implications for the development of effective tools and strategies for identifying and combating illicit activities on the dark web, ultimately contributing to a safer and more secure online environment.