AI-Driven Defense Mechanisms for Web Application Vulnerabilities
Aadi Chawla
Delhi Public School, RK Puram, New Delhi
Download PDFAbstract
Web applications are at the center of the digital environment, but also the greatest targets for exploitation of vulnerabilities such as SQL Injection (SQLi), Cross-Site Scripting (XSS), Cross-Site Request Forgery (CSRF), and Server-Side Request Forgery (SSRF). High-profile exploits involving the Equifax data breach (2017) via SQL Injection, the Yahoo Mail XSS site attack (2013) resulting in user session compromise, the CSRF vulnerability affecting GitHub (2019) authorizing behaviour in repositories, and the Capital One SSRF exploit (2019) that compromised over 100 million customer records exemplify how destructive exploits in these attack vectors can become. Legacy signature-based web application firewalls (WAFs) and static rule engines often fall short of effectively detecting evolving or obfuscated attack payloads. AI and ML can circumvent these limitations by providing adaptive, context-aware detection that is able to detect both known and zero-day threats.
Keywords: Artificial Intelligence; Web Application Firewall; Cybersecurity; SQL Injection; Cross-Site Scripting; CSRF; SSRF; Deep Learning
- Alghawazi, M., Alghazzawi, D., & Alarifi, S. (2022). Detection of SQL Injection Attack Using Machine Learning Techniques: A Systematic Literature Review. Journal of Cybersecurity and Privacy, *2*(4), 764–777. https://doi.org/10.3390/jcp2040039
- Alam, M., [et al.] (2024). Deep Learning-Based Detection of SSRF and Related Application-Layer Attacks. Sensors, *24*(6), 3215. https://doi.org/10.3390/s24063215
- Bhusal, S., [et al.] (2023). Deep Learning Technique-Enabled Web Application Firewall for the Detection of Web Attacks. Sensors, *23*(4), 2073. https://doi.org/10.3390/s23042073
- El Hajj, A., [et al.] (2024). Machine Learning Techniques for Detecting Cross-Site Request Forgery Attacks in Web Applications. IEEE Access, *12*. https://doi.org/10.1109/ACCESS.2024.3352714
- Fang, Y., [et al.] (2018). Cross-Site Scripting Detection Based on Deep Learning (DeepXSS). Proceedings of the ACM Conference on Data and Application Security and Privacy (CODASPY). https://doi.org/10.1145/3194452.3194469
- Shen, R., & Mitra, T. (2023). Server-Side Request Forgery Attack Detection Using Hybrid Anomaly Models. Computers & Security, *131*, 103879. https://doi.org/10.1016/j.cose.2023.103879