M. Fatima,
Ritik Lodhi,
Ashika Bajpai,
Keshav Pachlaniya,
Ruchika Nagle,
Sourabh Kumar,
- Professor, Department of Artificial Intelligence & Machine Learning (AIML), Computer Science & Engineering – Cyber Security (CSE-CS), (SIRT) Sagar Institute of Research and Technology, Madhya Pradesh, India
- Student, Department of Artificial Intelligence & Machine Learning (AIML), Computer Science & Engineering – Cyber Security (CSE-CS), (SIRT) Sagar Institute of Research and Technology, Madhya Pradesh, India
- Student, Department of Artificial Intelligence & Machine Learning (AIML), Computer Science & Engineering – Cyber Security (CSE-CS), (SIRT) Sagar Institute of Research and Technology, Madhya Pradesh, India
- Student, Department of Artificial Intelligence & Machine Learning (AIML), Computer Science & Engineering – Cyber Security (CSE-CS), (SIRT) Sagar Institute of Research and Technology, Madhya Pradesh, India
- Student, Department of Artificial Intelligence & Machine Learning (AIML), Computer Science & Engineering – Cyber Security (CSE-CS), (SIRT) Sagar Institute of Research and Technology, Madhya Pradesh, India
- Student, Department of Artificial Intelligence & Machine Learning (AIML), Computer Science & Engineering – Cyber Security (CSE-CS), (SIRT) Sagar Institute of Research and Technology, Madhya Pradesh, India
Abstract
This research investigates the use of deep learning techniques for the real-time detection of malicious activities in web traffic and proposes an intelligent, AI-driven Web Application Firewall (WAF) designed to provide automated and adaptive security. The system analyzes diverse components of HTTP requests, including request methods, URLs, headers, cookies, and payload content, to accurately identify and classify malicious behavior. The proposed model targets a wide range of common and critical web-based attacks, such as SQL Injection, Cross-Site Scripting (XSS), Path Traversal, and HTML Injection, which continue to pose serious threats to modern web applications The primary objective of this work is to design, implement, and deploy a robust security mechanism capable of classifying incoming web requests as either benign or malicious in real time. Upon detection, the system actively mitigates threats by blocking, logging, or flagging suspicious traffic for further analysis. The training process relies on a labeled dataset composed of HTTP request logs collected from intentionally vulnerable web applications, ensuring exposure to realistic attack patterns. By learning behavioral relationships across multiple request attributes, the deep learning model demonstrates strong generalization capabilities across different attack vectors. When integrated into a live web environment, the proposed intelligent WAF provides dynamic protection that adapts to evolving attack techniques, thereby enhancing the overall resilience and security posture of web applications.
Keywords: AI, deep learning, HTTP traffic, machine learning, web application firewall, XSS
[This article belongs to Journal of Computer Technology & Applications ]
References
- Hernández JA, Solís-Pérez JE, Parrales A, Mata A, Colorado D, Huicochea A, Gómez-Aguilar JF. A conformable artificial neural network model to improve the void fraction prediction in helical heat exchangers. International Communications in Heat and Mass Transfer. 2023 Nov 1;148:107035. 1016/j.icheatmasstransfer.2023.107035
- Elman JL. Finding structure in time. Cognitive Science. 1990 Mar;14(2):179–211. https://doi.org/10.1207/s15516709cog1402_1
- Monner D, Reggia JA. A generalized LSTM-like training algorithm for second-order recurrent neural networks. Neural Networks. 2012 Jan 1;25:70–83. doi:10.1016/j.neunet.2011.07.003.
- Alazmi S, De Leon DC. A systematic literature review on the characteristics and effectiveness of web application vulnerability scanners. IEEE Access. 2022 Mar 22;10:33200–19. 10.1109/ACCESS.2022.3161522
- Goodfellow I, Bengio Y, Courville A. Deep Learning. 1st edition. Cambridge, USA: MIT Press; 2016. pp. 1–800.
- Sommer R, Paxson V. Network Intrusion Detection. In: IEEE, editors. 2010 IEEE Symposium on Security and Privacy. Oakland, USA: IEEE; 2010. pp. 305–316.
- Ito M, Iyatomi H. Web application firewall using character-level convolutional neural network. In: 2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA). Penang, Malaysia: IEEE; 2018. pp. 103–106.
- Moradi Vartouni A, Teshnehlab M, Sedighian Kashi S. Leveraging deep neural networks for anomaly-based web application firewall. IET Information Security. 2019 Jul;13(4):352–361.
- Sharma S, Zavarsky P, Butakov S. Machine learning based intrusion detection system for web-based attacks. In: 2020 IEEE 6th International Conference on Big Data Security on Cloud. Baltimore, USA: IEEE; 2020. pp. 227–230.
- Scano C, Floris G, Montaruli B, Demetrio L, Valenza A, Compagna L, Ariu D, Piras L, Balzarotti D, Biggio B. ModSec-Learn: Boosting ModSecurity with Machine Learning. In: Distributed Computing and Artificial Intelligence. Cham, Switzerland: Springer Nature Switzerland; 2024. pp. 23–33.
Journal of Computer Technology & Applications
| Volume | 17 | |
| Issue | 01 | |
| Received | 15/01/2026 | |
| Accepted | 23/01/2026 | |
| Published | 10/02/2026 | |
| Publication Time | 26 Days |