Hardware and software for distributed and supercomputer systems

Research Article

Quantum machine learning methods for intrusion detection in software-defined networks

Il'ya Andreevich Antonov¹, Il'ya Il'ich Kurochkin²

1	National University of Science and Technology MISIS, Moscow, Russia
2	Institute for Information Transmission Problems of RAS, Moscow, Russia
1	m1908142@edu.misis.ru

Abstract. Software-defined network architecture is the preferred way to build large computer networks that require high responsiveness to change and a high degree of automation. The main feature of this architecture is the centralized management of the entire network from a single controller. However, this approach opens new opportunities for attacks on the network, making the controller their main target. This paper explores the possibility of applying quantum machine learning models to detect such attacks. (In Russian).

Keywords: software-defined networks, information security, machine learning, neural networks, quantum computing, intrusion detection systems, SDN, IDS

MSC-2020 65Y05; 68Q10

For citation: Il'ya A. Antonov, Il'ya I. Kurochkin. Quantum machine learning methods for intrusion detection in software-defined networks. Program Systems: Theory and Applications, 2025, 16:3, pp. 3–22. (In Russ.). https://psta.psiras.ru/2025/3_3-22.

Full text of article (PDF): https://psta.psiras.ru/read/psta2025_3_3-22.pdf.

The article was submitted 10.03.2025; approved after reviewing 26.04.2025; accepted for publication 22.05.2025; published online 18.07.2025.