INCREASING THE EFFICIENCY OF CYBER ATTACK DETECTION BY DESIGNING A NETWORK ANOMALIES ANALYSIS SYSTEM
DOI:
https://doi.org/10.30888/2709-2267.2025-33-00-033Keywords:
network anomalies, cybersecurity, intrusion detection, machine learning, network traffic, system architecture, data analysisAbstract
The article presents the design of a system for detecting and analyzing network anomalies. A modular architecture is proposed with data collection, preprocessing, analysis, and visualization modules. Experimental testing was performed in Cisco Packet TracReferences
Cybersecurity trends for 2025: how to protect your business / Kyivstar Business Hub [Electronic resource]. – 2025. – Access mode: https://hub.kyivstar.ua/articles/ostanni-trendy-kiberbezpeky
FoSDeT: a hybrid machine learning model for detecting Internet of Things botnets [Electronic resource] // Scientific Bulletin of the National University of Oil and Gas. – 2025. – No. 1. – Access mode: https://www.nvngu.in.ua/index.php/uk/vidavnitstvo/pro-zhurnal/1920-ukrcat/arkhiv-zhurnalu/2025/zmist-1-2025/7160-104
Sytnik, P. Y. Analysis of threats to data security in a network environment / P. Y. Sytnik // Information Security. – 2022. – No. 1. – P. 18–23.
Reis, M.J.C.S. AI-Driven Anomaly Detection for Securing IoT Devices in 5G-Enabled Smart Cities. Electronics 2025, 14, 2492. https://doi.org/10.3390/electronics14122492
Furikata, D. V., & Vakalyuk, T. A. (2025). Theoretical approaches to detecting anomalies in meter readings in scientific literature. Technical Engineering, (1(95), 325–331. https://doi.org/10.26642/ten-2025-1 (95)-325-331.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
