EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Adaptive Web Vulnerability Scanner Using Python-Based Reinforcement Learning Framework

Satyaprakash Sethy, Binay Munda Shibashish, Dandsena ., Rakesh Jagadev

International Journal of Innovative Science and Research Technology · 06.06.2026 · 3355

DOI: 10.38124/ijisrt/26may1465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 06.06.2026. Verfasst von Satyaprakash Sethy und 3 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of web-based applications and cloud-enabled services has significantly increased cybersecurity threats targeting modern web environments. Traditional web vulnerability scanners mainly depend on static payload signatures and predefined attack rules, resulting in high false positive rates, limited adaptability, and poor performance in dynamic web applications. To address these limitations, this research proposes an AI-driven adaptive web vulnerability scanner using a Python-based reinforcement learning framework. The proposed system integrates intelligent web crawling, automated form extraction, adaptive payload injection, vulnerability response analysis, and reinforcement learning-based attack optimization for efficient web application security assessment. The framework models the scanning process as a Markov Decision Process (MDP) and utilizes the Proximal Policy Optimization (PPO) algorithm to dynamically learn optimal attack strategies based on environmental rewards. The developed architecture supports detection of major web vulnerabilities including Cross-Site Scripting (XSS) and SQL Injection (SQLi) using adaptive payload mutation techniques. Experimental evaluation was performed using vulnerable web platforms such as DVWA and OWASP Juice Shop in a Google Colab environment using Python libraries including Selenium, BeautifulSoup, Requests, Gymnasium, and StableBaselines3. Experimental results demonstrated improved vulnerability detection accuracy, reduced false positive rate, and enhanced adaptive attack capability compared with traditional static payload scanners. The reinforcement learning agent progressively optimized action selection and improved attack efficiency through continuous interaction with the target environment. The proposed framework also provides extensibility for future integration of deep learning, API security analysis, cloud-native vulnerability assessment, and large language model-assisted penetration testing systems. The obtained results indicate that AI-assisted adaptive cybersecurity frameworks can significantly improve automated web vulnerability detection in modern dynamic web application.

Zitieren

APA

Sethy, S., Shibashish, B. M., ., D., & Jagadev, R. (2026). AI-Driven Adaptive Web Vulnerability Scanner Using Python-Based Reinforcement Learning Framework. International Journal of Innovative Science and Research Technology, 3355. https://doi.org/10.38124/ijisrt/26may1465

Vancouver

Sethy S, Shibashish BM, . D, Jagadev R. AI-Driven Adaptive Web Vulnerability Scanner Using Python-Based Reinforcement Learning Framework. International Journal of Innovative Science and Research Technology. 2026:3355. doi:10.38124/ijisrt/26may1465

BibTeX
@article{Sethy2026,
  author = {Sethy, Satyaprakash and Shibashish, Binay Munda and ., Dandsena and Jagadev, Rakesh},
  title = {AI-Driven Adaptive Web Vulnerability Scanner Using Python-Based Reinforcement Learning Framework},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {3355},
  doi = {10.38124/ijisrt/26may1465}
}
Kostenlos starten →