MACHINE LEARNING METHODS FOR PHISHING ATTACKS
Journal of Problems in Computer Science and Information Technologies · 2023
DOI: 10.26577/jpcsit.2023.v1.i2.02 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Problems in Computer Science and Information Technologies, 2023. Verfasst von Mirat Medelbekov und 2 weiteren Autor:innen.
Abstract (Originalsprache)
The basis of cybersecurity is an understanding of the mechanisms of social engineering. This increases the effectiveness in combating this type of manipulation. One of them is phishing. Phishing attacks actively exploit the human factor to collect credentials or distribute malware. Phishing websites are visually similar to real websites. Along with the development of technology, phishing methods have also evolved. Machine learning has been effectively used to identify and avoid phishing. The reason of this consider is to survey machine learning methods and the comes about of previous thinks about on the avoidance of phishing attacks. As well as our claim investigation and execution of a model for recognizing phishing sites. The efficiency of the demonstrate is moved forward by combining connected parameters. 5 calculations were utilized to prepare the show: Logistic Regression, Random Forest, Support Vector Machine(SVM), K-nearest neighbors algorithm(KNN) and KNN k-Fold Cross Validation.
Zitieren
APA
Medelbekov, M., Nurtas, M., & Altaibek, A. (2023). MACHINE LEARNING METHODS FOR PHISHING ATTACKS. Journal of Problems in Computer Science and Information Technologies. https://doi.org/10.26577/jpcsit.2023.v1.i2.02
Vancouver
Medelbekov M, Nurtas M, Altaibek A. MACHINE LEARNING METHODS FOR PHISHING ATTACKS. Journal of Problems in Computer Science and Information Technologies. 2023. doi:10.26577/jpcsit.2023.v1.i2.02
BibTeX
@article{Medelbekov2023,
author = {Medelbekov, Mirat and Nurtas, Marat and Altaibek, Aizhan},
title = {MACHINE LEARNING METHODS FOR PHISHING ATTACKS},
journal = {Journal of Problems in Computer Science and Information Technologies},
year = {2023},
doi = {10.26577/jpcsit.2023.v1.i2.02}
}
EUVIMED