Proceedings of TUSUR University / Archive / Issue of Journal № 2, t. 26, 2023 / Features of building neural networks taking into account the specifics of their training to solve the tasks of searching for network attacks

Features of building neural networks taking into account the specifics of their training to solve the tasks of searching for network attacks

DOI: 10.21293/1818-0442-2023-26-2-42-50

Download article in PDF format

JATS xml

Abstract: The problems of building neural networks to solve the prob-lems of detecting network intrusions, taking into account mod-ern publicly available technologies, are considered. Several configurations of neural networks are analyzed: a simple per-ceptron, a combined network consisting of two interconnected networks, simplified networks based on a simple perceptron, LSTM networks using hidden layers with data compression function. The weaknesses and strengths of neural network ar-chitectures are considered, taking into account the specifics of their training based on abnormal traffic datasets in intrusion detection tasks.

Keywords: network attack, neural network, dataset, feature matrix, activation function, Python programming language

For citation:
Vetrov I. A., Podtopelnyy V. V. Features of building neural networks taking into account the specifics of their training to solve the tasks of searching for network attacks. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2023, vol. 26, no. 2, pp. 42–50. DOI: 10.21293/1818-0442-2023-26-2-42-50

Authors and copyright holders:

Vetrov I. A. , I. Kant Baltic Federal University (Kaliningrad, Russia)
Podtopelnyy V. V. , Kaliningrad State Technical University (Kaliningrad, Russia)

1. Panchenko A.A., Anikienko M.V., Przhegorlinsky V.N [Analysis of approaches to building an information security system based on a data processing model]. Vestnik of Ryazan State Radioengineering University, 2005, no. 16, pp. 120–123 (in Russ.).
2. Goryunov M.N., Matskevich A.G., Rybolovlev D.A. [Synthesis of a machine learning model for detecting computer attacks based on the CICIDS2017 dataset]. Proceedings of the Institute for System Programming of the Russian Academy of Sciences, 2020, vol. 32, iss. 5, pp. 81–93 (in Russ.).
3. Goryunov M.N., Rybolovlev A.A., Rybolovlev D.A. [Evaluation of the applicability of machine learning methods for detecting computer attacks]. Information Systems and Technologies, 2020, no. 6, pp. 103–111 (in Russ.).
4. Goncharov V.A., Przhegorlinsky V.N. [Investigation of the possibilities of countering network information attacks by protected operating systems and information attack detection systems]. Vestnik of Ryazan State Radioengineering University, 2007, no. 20, pp. 10–14 (in Russ.).
5. Goncharov V.A., Przhegorlinsky V.N. [Method of detecting network attacks based on cluster analysis of interaction of computer network nodes]. Vestnik of Ryazan State Radioengineering University, 2011, no. 36, pp. 3–10 (in Russ.).
6. Geron A. Prikladnoe mashinnoe obuchenie s pomoshch'yu Scikit-Learn i TensorFlow: koncepcii, instrumenty i tekhniki dlya sozdaniya intellektual'nyh sistem [Applied machine learning using the scikit package-learn and TensorFlow: concepts, tools and techniques for creating intelligent systems]. St. Petersburg, Alfa-book, 2018. 688 p. (in Russ.).
7. Intrusion Detection Evaluation Dataset (CIC-IDS2018). Available at: https://www.unb.ca/cic/datasets/ids-2018.html (Accessed: April 02, 2022).
8. Leskovets J., Rajaraman A., Ulman J. Intelligent Analysis of Massive Data Sets. Cambridge, Cambridge University Press, 2014, 476 p.
9. Domingos P. A few useful things you need to know about machine learning. ACM Communications, 2012, vol. 55, no. 10, pp. 78–87.
10. Kostas K. Anomaly detection in networks using machine learning. Essex, School of Computer Science and Electronic Engineering University of Essex, 2018, 70 p.