Tharun G, Rohan M, Kiran Kumar, Sankeerth S, Thanushree Patel B S

DOI: https://doi.org/10.5281/zenodo.22032605

Web Applications are an integral part of today’s technological age, carrying out various applications in areas like healthcare, financial institutions, education, e-commerce, and government. Meanwhile, web application development has created a growing number and variety of cyber threats, with some of the most common being SQL injection (SQLi), XSS, CSRF, authentication bypasses, and more. The traditional cybersecurity mechanisms (e.g., vulnerability scanner tools, penetration testing) have proven to be inadequate, however, with respect to multiple factors that are inherent in the existing web environment, such as false positives, non-adaptability, lack of scalability, or a high level of human interaction. In this context, the recent developments in Artificial Intelligence (AI), machine learning (ML), Large Language Models (LLMs), and intelligent penetration testing (IPT) brought several novel solutions to the challenge of web application security and enabled intelligent and self-adaptive security systems. This paper, therefore, reviews the literature on the most recent developments in the area of intelligent web security, such as AI vulnerability detection, intelligent penetration testing, intelligent scanners and multi-agent systems, and the application of LLMs in cybersecurity. This paper aims to provide an introduction to the AI-powered web security system and discuss the need for adaptive and scalable and intelligent cybersecurity approaches to enhance the effectiveness of vulnerability detection.

Research papers: Artificial Intelligence, Web Application Security, Vulnerability Discovery, Automatic Penetration Testing, Machine Learning, Large Language Models (LLM), Cyber, Security, SQL Injection, Cross Site Scripting (XSS), Ethical Hacking, Security Automation, Multi-agent, Vulnerability Assessment.

This study of the literature takes a look at how Artificial Intelligence is used to make web application security better. It does this by finding weaknesses and doing penetration testing. The study looks at research on using Machine Learning and Deep Learning to improve the security of websites. It also looks at Large Language Models and Multi-Agent Systems. The goal is to make cybersecurity solutions more accurate and efficient. The researchers looked at the parts of these systems and how they are put together. They also looked at what the systems can. Cannot do. They compared the results of using these technologies. The results show that using Artificial Intelligence to deal with cybersecurity issues is an idea. However there are some problems with using Artificial Intelligence. For example sometimes it gives results. It is also hard to understand how it works. There is not data to make it work well. It is also hard to make it work with systems. All these problems make it hard to use Artificial Intelligence for cybersecurity. So future research should focus on making Artificial Intelligence systems for cybersecurity that work well and are flexible. The future of Artificial Intelligence-driven web security systems should be the focus of this research. Artificial Intelligence-driven web security systems are the key, to making the web a safer place.

I. Kertusha, G. Assres, O. Duman, and A. Arcuri, “A Survey on Web Testing: On the Rise of AI and Applications in Industry,” Science of Computer Programming, 2026, doi: 10.1016/j.scico.2026.103473.
[2] S. S. Mahmood, “SQL Injection Detection Using Machine Learning and Explainability,” Journal of Internet Services and Information Security, vol. 15, no. 2, pp. 309–324, 2025, doi: 10.58346/JISIS.2025.I2.022.
[3] A. Zhuravchak, A. Piskozub, B. Skorynovych, Y. Lakh, D. Zhuravchak, P. Hlushchenko, P. Venherskyi, I. Beliaiev, M. Vorokhob, and I. Kolbasynskyi, “Design and Development of a Large Language Model-Based Tool for Vulnerability Detection,” Eastern-European Journal of Enterprise Technologies, vol. 2, no. 2 (134), pp. 75–83, 2025, doi: 10.15587/1729-4061.2025.325251.
[4] M. A. Ahmed, “An Adaptive AI-Enhanced Automated Web Security Scanner with Multi-Vector Testing and Vulnerability Chaining,” 2025.
[5] Y. Stefinko, A. Piskozub, and A. Obshta, “Analysis of Vulnerability Characteristics for Automated Penetration Testing,” in Proc. IEEE Conference, 2024, pp. 449–453.
[6] V. Saber, A. M. Bahaa-Eldin, D. ElSayad, and Z. Fayed, “Automated Penetration Testing, A Systematic Review,” in Proc. 2023 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), 2023, pp. 373–378, doi: 10.1109/MIUCC58832.2023.10278377.
[7] P. Zhang, D. Zhang, L. Han, W. Wang, H. Wu, and Q. Zhao, “Automated Security Penetration Testing Based on Machine Learning,” 2024.
[8] B. Singh, “Automating Security Testing in CI/CD Pipelines Using DevSecOps Tools: A Comprehensive Study,” Science, Technology and Development, vol. IX, no. XII, p. 631, 2020.
[9] N. Rane and A. Qureshi, “Comparative Analysis of Automated Scanning and Manual Penetration Testing for Enhanced Cybersecurity,” in Proc. IEEE, 2024.
[10] S. Oladele and F. Lawal, “The Impact of AI-Assisted Code Generation on Software Vulnerabilities and the Role of AI in Automated Security Testing,” SSRN, 2025.
[11] S. O. Alwabisi, “AI in Penetration Testing: A Systematic Mapping Study,” TechRxiv, Jun. 27, 2025, doi: 10.36227/techrxiv.175099664.46246512/v1.
[12] M. Kozlovska, A. Piskozub, and V. Khoma, “Artificial Intelligence in Penetration Testing: Leveraging AI for Advanced Vulnerability Detection and Exploitation,” Advances in Cyber-Physical Systems, vol. 10, no. 1, pp. 65–72, 2025, doi: 10.23939/acps2025.01.065.
[13] A. Goutam and V. Tiwari, “Vulnerability Assessment and Penetration Testing to Enhance the Security of Web Application,” 2024.
[14] G. Sanchez, O. Olayinka, and A. Pasikhani, “Web Application Penetration Testing with Artificial Intelligence: A Systematic Review,” 2024.

Tharun G, Rohan M, Kiran Kumar, Sankeerth S, Thanushree Patel B S (2026). Intelligent Web Security Systems: A Literature Survey on AI-Driven Vulnerability Detection and Automated Penetration Testing. International Journal of Computer Science Engineering Techniques, 10(4), 94–99. ISSN: 2455-135X. DOI: https://doi.org/10.5281/zenodo.22032605