Machine Learning Models Stacking in the Malicious Links Detecting

Khukalenko, Yevhenii; Stopochkina, Iryna; Ilin, Mykola

Machine Learning Models Stacking in the Malicious Links Detecting

Дата

2023

Автори

Khukalenko, Yevhenii

Stopochkina, Iryna

Ilin, Mykola

Видавець

Igor Sikorsky Kyiv Polytechnic Institute

Анотація

An analysis of the performance of various classifiers on address and network groups of features was performed. A new classification model is proposed, which is a stacking of 3 models: kNN, XGBoost and Transformer. The best model for stacking was experimentally determined: Logistic Regression, which made it possible to improve the result of the best available model by 3%. The hypothesis that stacking a larger number of worse models has an advantage over stacking a smaller number of more productive models on the used data set was confirmed: regardless of the choice of stacking metaalgorithm, stacking of three models showed better results than stacking two.

Ключові слова

Malicious URL, Machine Learning, Stacking

Бібліографічний опис

Khukalenko, Ye. Machine Learning Models Stacking in the Malicious Links Detecting / Yevhenii Khukalenko, Iryna Stopochkina, Mykola Ilin // Theoretical and Applied Cybersecurity : scientific journal. – 2023. – Vol. 5, Iss. 1. – Pp. 67–79. – Bibliogr. 33 ref.