Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

DETECTION OF NETWORK ATTACKS USING THE RANDOM FOREST METHOD IN CONDITIONS OF UNBALANCED DATA

Kulikova Olga Vitalievna  (Associate Professor of the Department of Physical and Mathematical Sciences, Don State Technical University, Rostov-on-Don )

Pinigin Andrey Sergeevich  (Don State Technical University, Rostov-on-Don)

The article is devoted to the topic of detecting attacks using the random forest method in conditions of unbalanced data. This article presents the application of the Random Forest machine learning method for detecting and classifying network attacks based on network traffic analysis. The stages of preparing the selected CICIDS2017 dataset are described, including removing correlating features, balancing classes, and selecting the most significant features. Special attention is paid to modifying the model by adjusting the class weights and optimizing the hyperparameters of the model, which made it possible to increase the accuracy of detecting rare types of attacks. The results of the study showed the effectiveness of using ensemble methods in the task of classifying network attacks, the possibility of using a random forest in real intrusion detection systems (IDS).

Keywords:machine learning, random forest, attack classification, network traffic analysis, class balancing.
 

Read the full article …

Citation link:
Kulikova O. V., Pinigin A. S. DETECTION OF NETWORK ATTACKS USING THE RANDOM FOREST METHOD IN CONDITIONS OF UNBALANCED DATA // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2025. -№06/2. -С. 123-127 DOI 10.37882/2223-2966.2025.06-2.18
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences