URLYZER: a system for identifying malicious URLs using AI to support decision-making
DOI:
https://doi.org/10.5753/reic.2022.2309Abstract
This work presents the URLYZER, a system for identifying malicious URLs. As most resources on the web are accessed via an URL, it can be modified or spoofed for misuse. With this, URLYZER aims to analyze the URL, from the extraction of the lexical characteristics, and using a Random Forest classifier to determine whether a given URL is benign or malignant. The classifier obtained satisfactory results according to related works, with an accuracy of 86%, 79% precision, 98% recall, and 88% in the F1-score.
Downloads
References
Ayres, L. D. G., Brito, I. V. S., Gomes, R. R., et al. (2019). Utilizando aprendizado de máquina para detecção automática de urls maliciosas brasileiras. In Anais Principais do XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 972–985. SBC.
Bezzera, M. A. e Feitosa, E. (2015). Investigando o uso de características na detecção de urls maliciosas. In XV Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais, pages 100–113. SBC.
Darling, M., Heileman, G., Gressel, G., Ashok, A., e Poornachandran, P. (2015). A lexical approach for classifying malicious urls. In 2015 International Conference on High Performance Computing & Simulation (HPCS), pages 195–202. IEEE.
Feroz, M. N. e Mengel, S. (2015). Phishing url detection using url ranking. In 2015 IEEE International Congress on Big Data, pages 635–638. IEEE.
Ma, J., Saul, L. K., Savage, S., e Voelker, G. M. (2009). Beyond blacklists: learning to detect malicious web sites from suspicious urls. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1245–1254.
Nguyen, H. H. e Nguyen, D. T. (2016). Machine learning based phishing web sites detection. In AETA 2015: Recent Advances in Electrical Engineering and Related Sciences, pages 123–131. Springer.
Sahoo, D., Liu, C., e Hoi, S. C. (2017). Malicious url detection using machine learning: A survey. arXiv preprint arXiv:1701.07179.
Vanhoenshoven, F., Nápoles, G., Falcon, R., Vanhoof, K., e Köppen, M. (2016). Detecting malicious urls using machine learning techniques. In 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pages 1–8. IEEE.
Verma, R. e Das, A. (2017). What’s in a url: Fast feature extraction and malicious url detection. In Proceedings of the 3rd ACM on International Workshop on Security and Privacy Analytics, pages 55–63.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 The authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
