Detection of phishing portals through machine learning algorithms
Objective Analysis and practical implementation of the phishing portal detection functionality through machine learning algorithms. Method. Systematization of disparate information, analysis of the field, description of available developments are the main methods that were used in the study. The wor...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Dagestan State Technical University
2024-10-01
|
| Series: | Вестник Дагестанского государственного технического университета: Технические науки |
| Subjects: | |
| Online Access: | https://vestnik.dgtu.ru/jour/article/view/1567 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849410158602485760 |
|---|---|
| author | E. A. Trushnikov |
| author_facet | E. A. Trushnikov |
| author_sort | E. A. Trushnikov |
| collection | DOAJ |
| description | Objective Analysis and practical implementation of the phishing portal detection functionality through machine learning algorithms. Method. Systematization of disparate information, analysis of the field, description of available developments are the main methods that were used in the study. The work is divided into three large sub-blocks. The first one analyzes the concept of machine learning, describes the main ways to correctly interpret the information entered, indicates the most popular techniques and databases. In the second part of the work, an analysis of artificial neural networks is carried out. In particular, their subspecies are shown with a description of the implementation features, and a comparison with living neurons is carried out. In the third part, the practical implementation of the two techniques and their comparison are carried out, recommendations are given regarding their use in detecting phishing portals. Result. The paper investigates the methods of analyzing phishing portals. The analysis showed that it is most rational to use a random forest, because it provides quality according to the precession, recall, F1-score, 98% metrics with a significant number of parametric values entered. Conclusions. When implementing various search methodologies for phishing portals, it is necessary to take into account their decrease in efficiency from the entered parameters. To do this, it is important to conduct preliminary tests. However, the test result can be interpreted in different ways. In particular, the effectiveness of the methods can be improved if you limit the number of input parameters, but at the same time rigidly structured according to one search criterion. |
| format | Article |
| id | doaj-art-07ed6ffd90574b0390cd4fdf45e5c9fc |
| institution | Kabale University |
| issn | 2073-6185 2542-095X |
| language | Russian |
| publishDate | 2024-10-01 |
| publisher | Dagestan State Technical University |
| record_format | Article |
| series | Вестник Дагестанского государственного технического университета: Технические науки |
| spelling | doaj-art-07ed6ffd90574b0390cd4fdf45e5c9fc2025-08-20T03:35:14ZrusDagestan State Technical UniversityВестник Дагестанского государственного технического университета: Технические науки2073-61852542-095X2024-10-0151315416210.21822/2073-6185-2024-51-3-154-162916Detection of phishing portals through machine learning algorithmsE. A. Trushnikov0Moscow Technical University of Communication and InformaticsObjective Analysis and practical implementation of the phishing portal detection functionality through machine learning algorithms. Method. Systematization of disparate information, analysis of the field, description of available developments are the main methods that were used in the study. The work is divided into three large sub-blocks. The first one analyzes the concept of machine learning, describes the main ways to correctly interpret the information entered, indicates the most popular techniques and databases. In the second part of the work, an analysis of artificial neural networks is carried out. In particular, their subspecies are shown with a description of the implementation features, and a comparison with living neurons is carried out. In the third part, the practical implementation of the two techniques and their comparison are carried out, recommendations are given regarding their use in detecting phishing portals. Result. The paper investigates the methods of analyzing phishing portals. The analysis showed that it is most rational to use a random forest, because it provides quality according to the precession, recall, F1-score, 98% metrics with a significant number of parametric values entered. Conclusions. When implementing various search methodologies for phishing portals, it is necessary to take into account their decrease in efficiency from the entered parameters. To do this, it is important to conduct preliminary tests. However, the test result can be interpreted in different ways. In particular, the effectiveness of the methods can be improved if you limit the number of input parameters, but at the same time rigidly structured according to one search criterion.https://vestnik.dgtu.ru/jour/article/view/1567phishingmachine learningneural networksportal analysis |
| spellingShingle | E. A. Trushnikov Detection of phishing portals through machine learning algorithms Вестник Дагестанского государственного технического университета: Технические науки phishing machine learning neural networks portal analysis |
| title | Detection of phishing portals through machine learning algorithms |
| title_full | Detection of phishing portals through machine learning algorithms |
| title_fullStr | Detection of phishing portals through machine learning algorithms |
| title_full_unstemmed | Detection of phishing portals through machine learning algorithms |
| title_short | Detection of phishing portals through machine learning algorithms |
| title_sort | detection of phishing portals through machine learning algorithms |
| topic | phishing machine learning neural networks portal analysis |
| url | https://vestnik.dgtu.ru/jour/article/view/1567 |
| work_keys_str_mv | AT eatrushnikov detectionofphishingportalsthroughmachinelearningalgorithms |