Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178127,
        author = {Sibikarthik B K and ASAN NAINAR M},
        title = {ML-Enhanced Behavioral & Anomaly Detection Web Application Firewall},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {5972-5979},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178127},
        abstract = {Traditional firewalls are frequently unable to identify complex user-based threats in the constantly changing field of web security. A Machine Learning-Enhanced Behavioral and Anomaly Detection Web Application Firewall (WAF) is presented in this research. It actively tracks, examines, and reacts to unusual user activity. Two web applications are used to implement the system: a secure application with anomaly detection features and another that is purposefully left open for passive observation. A real-time dashboard is available in both applications to track user entry and exit times as well as behavioral trends.
Comprehensive behavior tracking is made possible via MongoDB, which acts as the backend for gathering and storing activity records. By examining input payloads and user interaction sequences, the secure application uses a trained machine learning model that can recognize different attack patterns, including brute force, XSS, and SQL injection. Potential breaches are effectively avoided since the system immediately bans access and reroutes the user to the login page when it detects suspicious activity.
This research shows how to combine machine learning and behavioral analytics to improve web application defenses, providing a dynamic and flexible security solution that goes well beyond static rule-based solutions.},
        keywords = {},
        month = {May},
        }