XSS Attack Detection using Machine Learning Algorithms

Abstract

This project focuses on the development of an XSS attack detection system using machine learning algorithms. The research involves the careful curation of diverse datasets encompassing XSS attacks and benign data. Key features are extracted, emphasizing HTML structure and JavaScript patterns. The study evaluates the efficacy of k- Nearest Neighbors, Logistic Regression, Random Forest, and Support Vector Machines (SVM) in detecting XSS threats. The training phase optimizes model accuracy, and performance metrics such as Precision, Recall, and F1 Score assess the model's effectiveness. Results provide a comparative analysis of machine learning algorithms, offering insights for future implementations. The study contributes to strengthening web security, showcasing the potential of machine learning in XSS attack detection.