DEVELOPMENT OF A LINUX-BASED UTM SYSTEM USING GENERATIVE ARTIFICIAL INTELLIGENCE AND ENSEMBLE LEARNING TO DETECT URL-BASED PHISHING ATTACKS

Authors

  • Mamatov Islom Isomiddinovich Head of the Academic Affairs Department, Samarkand International University of Technology Author

Keywords:

phishing detection, malicious URLs, Unified Threat Management (UTM), Linux, generative artificial intelligence, ensemble learning, machine learning, cybersecurity, URL analysis, threat detection, artificial intelligence, network security.

Abstract

The rapid growth of web-based services and digital communication has contributed to the increasing prevalence and sophistication of URL-based phishing attacks. Traditional security mechanisms often struggle to detect newly generated and obfuscated phishing URLs, creating a need for intelligent and adaptive cybersecurity solutions. This study proposes the development of a Linux-based Unified Threat Management (UTM) system that integrates Generative Artificial Intelligence (Generative AI) and ensemble learning techniques for automated detection and classification of phishing URLs. The proposed system combines URL feature extraction, machine-learning-based classification, ensemble decision-making, and AI-assisted analysis within a Linux-based security architecture.

References

1.Basnet, R. B., Mukkamala, S., & Sung, A. H. (2008). Detection of phishing attacks: A machine learning approach. Studies in Computational Intelligence, 1–19.

2.Ma, J., Saul, L. K., Savage, S., & Voelker, G. M. (2009). Beyond blacklists: Learning to detect malicious web sites from suspicious URLs. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1245–1254.

3.Rao, R. S., & Pais, A. R. (2019). Detection of phishing websites using an efficient feature-based machine learning approach. Neural Computing and Applications, 31, 1–14.

4.Sahingoz, O. K., Buber, E., Demir, O., & Diri, B. (2019). Machine learning based phishing detection from URLs. Expert Systems with Applications, 117, 345–357.

5.Le, H., Pham, Q., Sahoo, D., & Hoi, S. C. H. (2018). URLNet: Learning a URL representation with deep learning for malicious URL detection. Proceedings of the 2018 ACM International Conference on Web Search and Data Mining, 1–9.

6.Xin, Y., Kong, L., Liu, Z., Chen, Y., Li, Y., Zhu, C., Gao, M., Hou, H., & Wang, C. (2018). Machine learning and deep learning methods for cybersecurity. IEEE Access, 6, 35365–35381.

7.Scarfone, K., & Mell, P. (2007). Guide to Intrusion Detection and Prevention Systems (IDPS). National Institute of Standards and Technology, Special Publication 800-94.

Downloads

Published

2026-08-20