Improving detection of cross-site scripting (XSS) attacks towards web application through comprehensive machine learning algorithms

Baharuddin, Basyiratul Ulfa (2024) Improving detection of cross-site scripting (XSS) attacks towards web application through comprehensive machine learning algorithms. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

Text (Full Text) Improving detection of cross-site scripting (XSS) attacks towards web application through comprehensive machine learning algorithms.pdf - Submitted Version Download (2MB)

Abstract

In today's rising digital world, Cross-Site Scripting (XSS) poses a significant security threat to web applications, enabling attackers to inject malicious code that compromise user data, hijack user sessions, and modify web content. Despite current detection methods, many systems have significant false positive rates and are not adaptable to new attack vectors. This study intends to improve XSS detection by using Machine Learning approaches, in conjunction with various feature selection methods. The study includes gathering and preprocessing a complete dataset, training and testing the machine learning model, and evaluating its performance against various XSS attack scenarios. The results indicate that the proposed method significantly improves detection accuracy and reduces false positives, providing a robust solution for safeguarding web applications. This study promotes online security by proposing a practical and adaptable strategy for detecting XSS vulnerabilities. The findings of this study show the potential for enhanced web application security and emphasize the need for future investigation of machine learning techniques in threat detection.

Actions (login required)

View Item