Research indexJournal article
Improving User Privacy Through Deep Learning: JavaScript Tracking Detection
Alqahtani, Frikha, Aljughaiman
2025 IEEE Twelfth International Conference on Communications and Networking (ComNet)4 Nov 2025
NobleIDark:/48914/w1/20260525/F3B821F5DOI10.1109/comnet68251.2025.11325482
Improving User Privacy Through Deep Learning: JavaScript Tracking Detection
Alqahtani, Frikha, Aljughaiman · 2025 IEEE Twelfth International Conference on Communications and Networking (ComNet) · 2025 · Subscription
NobleIDark:/48914/w1/20260525/F3B821F5DOI10.1109/comnet68251.2025.11325482
The full text is at the publisher
You can read the abstract here, or open it at the publisher.
Abstract
The web environment has evolved from being dominated by individual or organizational content creation to a complex web of interrelated webpages featuring content from various third-party websites involved in activities like advertising and analytics. This shift, while contributing to free content and innovation, has raised significant privacy concerns. Many researchers have increasingly focused on the privacy implications of third-party tracking of users’ browsing activities. This paper provides an overview of existing tools designed to defend against various tracking methods. It proposes a framework that utilizes deep learning to counteract tracking practices by classifying JavaScript asking or functional snippet and compares it with existing privacy tools. The aim is to empower users to gain control over their online privacy. This innovative solution leverages deep learning techniques to identify JavaScript programs and enhance privacy defenses, ultimately striving to strengthen privacy in the web tracking domain by preventing detection evasion through code.