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{195825,
        author = {G. Manohar Reddy and V. Ravi Chandu and B. Yogesh and M. Sai Ganesh and A. Sandhya Rani},
        title = {HYBRID WEB APPLICATION FIREWALL SYSTEM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1931-1938},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195825},
        abstract = {In the modern networked digital environment, web applications are everywhere so it is appealing to high-tech cyber-attackers. The conventional rule-based Web Application Firewalls (WAFs) serve as front line protections, yet fail to match up with the changing attack patterns, usually producing false positives or not noticing the zero-day exploits. The present paper is based on the recent findings that noted the possibility of using the concept of Machine Learning (ML) in the field of cybersecurity, including the combination of Multinomial Naive Bayes and Random Forest classifiers. An improved hybrid model is offered in the present paper. We present a 2-layered system that is a hybrid of Multinomial Naive Bayes (to perform supervised classification of known threats) and Autoencoder neural network (to perform unsupervised zero-day anomaly detection). We experimental results prove that the accuracy of the Naive Bayes as a baseline was 73.03, but when the Autoencoder integration was applied, the overall accuracy of detection was astonishingly high, reached 99.05, which is also far better than any traditional single-model ML analogy that is discussed in the existing literature.},
        keywords = {Web Application Firewall (WAF), Machine Learning, Deep Learning, Anomaly Detection, Zero-Day Exploits, Autoencoder, Multinomial Naive Bayes, Hybrid Architecture, Intrusion Detection, HTTP Traffic Analysis},
        month = {April},
        }