Research Article
Characterization of Malicious URLs Using Machine Learning and Feature Engineering
@INPROCEEDINGS{10.1007/978-3-031-51849-2_2, author={Sidwendluian Romaric Nana and Didier Bassol\^{e} and Jean Serge Dimitri Ouattara and Oumarou Si\^{e}}, title={Characterization of Malicious URLs Using Machine Learning and Feature Engineering}, proceedings={Innovations and Interdisciplinary Solutions for Underserved Areas. 6th EAI International Conference, InterSol 2023, Flic en Flac, Mauritius, September 16-17, 2023, Proceedings}, proceedings_a={INTERSOL}, year={2024}, month={2}, keywords={Malicious URL Characterization Feature Engineering Detection Classification}, doi={10.1007/978-3-031-51849-2_2} }- Sidwendluian Romaric Nana
Didier Bassolé
Jean Serge Dimitri Ouattara
Oumarou Sié
Year: 2024
Characterization of Malicious URLs Using Machine Learning and Feature Engineering
INTERSOL
Springer
DOI: 10.1007/978-3-031-51849-2_2
Abstract
In this paper, we use Machine Learning models for malicious URL detection and classification by Feature Engineering techniques. These models were implemented with scikit-learn using Random Forest, Support Vector Machine and XGBoost classifier algorithms. Our models were trained, tested, and then optimized with a dataset of 641,125 URLs (benign, defacement, malware, and phishing) from several sources including ISCX-URL2016 from the University of New Brunswick. Through iterative learning, we have shown that the combination of certain hyperparameters and features reduces the false positive rate. The results obtained are interesting with scores close to 100% and zero false positive rates for some types of URLs. We then evaluated the performance of the models against other related works models.
