ML based Web Application Firewall for Signature and Anomaly Detection Using Feature Extraction

In today’s digital landscape, web applications have become indispensable tools for businesses, facilitating access to vital data and services. However, this ubiquity also exposes them to a myriad of cyber threats, ranging from SQL injection to cross-site scripting. Traditional Web Application Firewalls (WAFs), while essential, often struggle with rule-based detection methods, leading to issues like false positives and an inability to adapt swiftly to emerging threats. This paper introduces an advanced Web Application Firewall (WAF) fortified with Machine Learning (ML) techniques, specifically a Random Forest classifier. The proposed WAF achieved nearly $\mathbf{1 0 0 \%}$ accuracy in classifying requests as normal or anomalous and $\mathbf{8 9. 5 \%}$ accuracy in distinguishing between different attack types. Furthermore, it significantly reduces computational time compared to traditional WAFs. By harnessing ML, the proposed WAF enhances web application security, effectively identifying and mitigating attacks while minimizing false positives, showcasing a practical ML-driven solution for safeguarding online assets against evolving cyber threats.