Automated Vulnerability Assessment in Web Applications through AI
Venkata Nagesh Boddapati, Gagan Kumar Patra
DOI: 10.63665/ijmlaidse-y1f2a002
View / Download Full Article (PDF)Abstract
Web applications, dealing with private information and providing substantial services, are a huge part of the digital infrastructure we use daily. Unfortunately, in many places, they are not that safe, hence becoming a common target of cybercriminals. Traditional vulnerability discovery is time-consuming and error-prone. AI made possible the automation of vulnerability assessment, enhancing its speed and accuracy. This research looks into the effectiveness of AI in independently finding security vulnerabilities in web applications. Various types of security holes, methods of security based on AI, and their efficiency with systems in place are discussed here. This study offers an empirical evaluation of AI-driven tools, presenting comparisons of their efficiency with those of more conventional methods. The results point to the need for further improvement, stressing at once the advantages and disadvantages of AI usage for the purpose of vulnerability assessment. Ideas for further research are included in the conclusion of the paper.
Keywords
Artificial Intelligence, Vulnerability Assessment, Web Security, Machine Learning, Cybersecurity, Automated Testing, Threat Detection, Deep Learning.
References
[1] Ahmad, M., Ghafoor, K. Z., Bakar, K. A., & Lloret, J. (2021). An AI-based vulnerability detection system for web applications. IEEE Access, 9, 74082–74095.
[2] Shirazi, M., & Stojanovic, N. (2020). Machine learning approaches for web application vulnerability detection. Journal of Information Security and Applications, 55, 102581.
[3] Chakraborty, S., Alam, M., & Saha, S. (2022). Deep learning-based intrusion detection systems: A comprehensive review. Computers & Security, 113, 102577.
[4] Sharma, P., Gupta, B., & Chatterjee, P. (2021). Use of AI in vulnerability management: Challenges and opportunities. Future Generation Computer Systems, 125, 544–559.
[5] Kim, J., & Kim, H. (2020). Adversarial attacks on deep learning-based malware detection systems. Security and Privacy, 3(1), e97.
[6] Wang, W., Zhu, M., Zeng, X., Ye, X., & Sheng, Y. (2017). Malware traffic classification using convolutional neural network for representation learning.
[7] Caceres, J., Cuadrado-Gallego, J. J., & Gutiérrez, C. (2021). A hybrid machine learning model for the automatic detection of vulnerabilities in web applications.
[8] Liu, H., Lang, B., Liu, M., & Yan, H. (2020). CNN and RNN-based payload classification methods for web application security.
[9] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks.
[10] Nasr, M., Shokri, R., & Houmansadr, A. (2018). Comprehensive privacy analysis of deep learning.
[11] Zou, D., Wang, S., Han, Y., Jin, H., & Li, S. (2019). Reinforcement learning-based adaptive security configuration for cloud applications.
[12] Koloseni, D., Pham, H. V., & Kim, D. S. (2022). Explainable AI for security: A survey.
[13] OWASP Foundation. (2021). OWASP Top 10 – 2021: The Ten Most Critical Web Application Security Risks.
[14] Amankwa, E., Gyamfi, E., & Forkuo, E. K. (2023). Enhancing cybersecurity threat detection using AI and machine learning models.
[15] Bostani, H., & Sheikhan, M. (2017). Hybrid of anomaly-based and signature-based IDS for detecting unknown attacks.