Machine Learning Powered Real Time Web Vulnerability Detection: Browser Extension for Website Security

Mishra, Sourabhkumar Shivbrat (2025) Machine Learning Powered Real Time Web Vulnerability Detection: Browser Extension for Website Security. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (618kB) | Preview

Abstract

The proliferation of web applications has led to a parallel increase in sophisticated cyber threats, with Cross-Site Scripting (XSS) and SQL Injection (SQLi) remaining among the most prevalent and damaging vulnerabilities. Traditional security measures often struggle to provide real-time, client-side protection. This research project addresses this gap by developing a dual-component solution: a high-accuracy machine learning model and a corresponding real-time browser extension. The core of the project is a Logistic Regression model trained on a diverse and augmented dataset of over 111,000 web payloads, achieving a remarkable 99.88% accuracy in distinguishing between malicious and benign inputs. This model uses a hybrid feature engineering approach of 30 hand crafted features and 1000 TF-IDF n-gram features. This model is practically realized through an Edge browser extension that passes user input and page content to our model and provides immediate visual feedback to users on potential threats. It then serves as a first line of defense against accidental submissions of malicious payloads. The evaluation shows the model's promising performance, and the extension's functionality to detect an abundance of XSS and SQLi attacks, thus certainly representing a development in proactive, user-focused web security.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Monaghan, Mark UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	18 Aug 2026 17:01
Last Modified:	18 Aug 2026 17:01
URI:	https://norma.ncirl.ie/id/eprint/9544

Actions (login required)

View Item