Журнал «Современная Наука»

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

ANALYSIS OF MACHINE LEARNING METHODS FOR ANOMALY DETECTION IN INTRUSION DETECTION SYSTEMS

Balyberdin Aleksei V.  (Financial University under the Government of the Russian Federation)

Intrusion Detection Systems are widely used to detect cyberattacks on corporate data transmission network. Detecting new and unknown cyberattacks on CDTN is an important task of IDS. Anomaly detection methods are used to detect such cyberattacks. The article presents a comparative analysis of machine learning methods used to detect anomalies in IDS. The purpose of this article is to systematize knowledge and formalize problems related to solving the problem of detecting anomalies in corporate data transmission networks (CDTN). The analysis of scientific papers on IDS anomaly detection methods was carried out according to the following parameters: year of publication of the article, name of the methods, data set, dimension of the feature space, types of anomalies, detection accuracy, environment of use and brief conclusions. The studied anomaly detection methods were divided into two categories: classical machine learning methods and hybrid methods. For each category, seven scientific papers were selected for analysis. The criteria for selecting these papers were the completeness of the description of the studies, the date of publication, the authority of the journal and the number of publications by the author. The result of the work is the systematization of existing knowledge, the formulation of problems and directions for further research of anomaly detection systems. The conclusions of the scientific article can be used for future research in this area.

Keywords:intrusion detection system, anomaly, machine learning methods, hybrid methods, data set, feature of data set, corporate data transmission networks, cyberattack
 

Read the full article …

Citation link:
Balyberdin A. V. ANALYSIS OF MACHINE LEARNING METHODS FOR ANOMALY DETECTION IN INTRUSION DETECTION SYSTEMS // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2024. -№11/2. -С. 67-76 DOI 10.37882/2223-2966.2024.11-2.38
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