Overcoming Tor: An Analysis of Video Fingerprinting Attacks with Machine Learning

Abstract

Terrorist groups and violent extremist organizations have taken advantage of the anonymity provided by The Onion Router (Tor). They use it to clandestinely distribute video media to recruit and spread propaganda as well as incite others to commit acts of terrorism. This thesis seeks to continue a line of work in developing machine learning algorithms to conduct video fingerprinting attacks on network traffic transmitted over Tor in a closed world environment. It will expand upon previous research by using multiple media platforms for videos being streamed. The end goal from this line of research is a future product that the Department of Defense can apply against real world network traffic to identify individuals using Tor and the dark web for recruiting, training, and incitement of terror as well as identify individuals that are actively being recruited.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2023
Accession Number
AD1224360

Entities

People

  • Trevor J. Thomas

Organizations

  • Naval Postgraduate School

Tags

Fields of Study

  • Computer science

Readers

  • Computer Networking
  • Distributed Systems and Data Platform Development
  • Political Violence and Terrorism Studies.

Technology Areas

  • AI & ML