The use of artificial neural networks to detect malicious software in radio engineering systems based on Linux operating systems

N.N. Samarin; E.Y. Pavlenko; D.S. Lavrova; E.A. Abramov

doi:10.18127/j00338486-202602-10

The use of artificial neural networks to detect malicious software in radio engineering systems based on Linux operating systems

N.N. Samarin¹, E.Y. Pavlenko², D.S. Lavrova³, E.A. Abramov⁴

research article UDC 004.05 Pages: 73-84 doi.org/10.18127/j00338486-202602-10

Keywords: Artificial neural networks transformer malware ELF files Linux

Abstract

The article proposes a method for detecting malware on widespread complex systems running Linux family operating systems. Experimental studies confirmed the effectiveness of the method: the best accuracy was 94.5%.

Received: 29.12.2025
Approved after review: 13.01.2026
Accepted: 28.01.2026

How to cite

Самарин Н.Н., Павленко Е.Ю., Лаврова Д.С., Абрамов Е.А. Применение искусственных нейронных сетей для обнаружения вредоносного программного обеспечения в радиотехнических системах на базе операционных систем семейства Linux // Радиотехника. 2026. № 2. С. 73–84. DOI: https://doi.org/10.18127/j00338486-202602-10

References

Exploits and vulnerabilities in Q1 2025 [Jelektronnyj resurs]. URL: https://securelist.com/vulnerabilities-and-exploits-in-q1-2025/116624/ (data obrashhenija 20.10.2025).
Linux malware: types, families and trends [Jelektronnyj resurs]. URL: https://any.run/cybersecurity-blog/linux-malware-types-families-and-trends/ (data obrashhenija 20.10.2025).
How to identify and remove linux malware infections [Jelektronnyj resurs]. URL: https://www.itprotoday.com/linux-os/how-to-identify-and-remove-linux-malware-infections (data obrashhenija 20.10.2025).
What are indicators of compromise (IoC) [Jelektronnyj resurs]. URL: https://www.cloudflare.com/ru-ru/learning/security/what-are-indicators-of-compromise/ (data obrashhenija 20.10.2025).
Onyebuchi O.B. Signature based network intrusion detection system using feature selection on android. Signature. 2020. V. 11. № 6. P. 551-558.
Punyasiri D.L.S. Signature & behavior based malware detection. Malabe. Sri Lanka: Sri Lanka Institute of Information Technology. 2023.
Sheluhin O.I., Rybakov S.Ju., Zvezhinskij S.S. Obnaruzhenie kiberatak i vredonosnogo programmnogo obespechenija nulevogo dnja metodami mashinnogo obuchenija. Radiotehnika. 2025. T. 89. № 8. S. 184-198. DOI: https://doi.org/10.18127/j00338486-202508-21 (in Russian).
Qamar R., Zardari B.A. Artificial neural networks: an overview. Mesopotamian Journal of Computer Science. 2023. V. 2023. P. 124-133.
Appalonov A.M., Maslennikova Ju.S., Sherstjukov O.N. Primenenie nejronnyh setej glubokogo obuchenija dlja analiza prostranstvennyh i vremennýh komponent razlozhenija polnogo jelektronnogo soderzhanija ionosfery. Radiotehnika. 2025. T. 89. № 1. S. 172-179. DOI: https://doi.org/10.18127/j00338486-202501-16 (in Russian).
Malygin I.V., Bel'kov S.A., Mihajlik D.A., Stafeev K.V. Razrabotka metodov formirovanija obrazcov, obuchajushhih nej-ronnuju set' obnaruzhivat' i klassificirovat' pomehi v strukture poleznogo signala. Radiotehnika. 2024. T. 88. № 6. S. 121-129. DOI: 10.18127/j00338486-202406-15 (in Russian).
Montesinos López O.A., Montesinos López A., Crossa J. Fundamentals of artificial neural networks and deep learning. Multivariate statistical machine learning methods for genomic prediction. Cham: Springer International Publishing. 2022. P. 379-425.
A Brief introduction to recurrent neural networks [Jelektronnyj resurs]. URL: https://towardsdatascience.com/a-brief-introduction-to-recurrent-neural-networks-638f64a61ff4/ (data obrashhenija 11.05.2025).
Taye M.M. Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation. 2023. V. 11. № 3. P. 52.
Zhao X. et al. A review of convolutional neural networks in computer vision. Artificial Intelligence Review. 2024. V. 57. № 4. P. 99.
Dosovitskiy A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. 2020.
Zhang M. Neural attention: Enhancing qkv calculation in self-attention mechanism with neural networks. arXiv preprint arXiv:2310.11398. 2023.
Bensaoud A., Kalita J. Deep multi-task learning for malware image classification. Journal of Information Security and Applications. 2022. V. 64. P. 103057.
Katar O., Yıldırım O. Classification of Malware Images Using Fine-Tunned ViT. Sakarya University Journal of Computer and Information Sciences. 2024. V. 7. № 1. P. 22-35.
Malware Bazaar Database [Jelektronnyj resurs]. URL: https://bazaar.abuse.ch/browse/tag/elf/ (data obrashhenija 11.05.2025).
Labeled-Elfs [Jelektronnyj resurs]. URL: https://github.com/nimrodpar/Labeled-Elfs/tree/main (data obrashhenija 11.05.2025).
Linux-malware [Jelektronnyj resurs]. URL: https://github.com/timb-machine/linux-malware/tree/main/malware/binaries (data obrashhenija 11.05.2025).
Linux-Malware-Samples [Jelektronnyj resurs]. URL: https://github.com/MalwareSamples/Linux-Malware-Samples (data obrashhenija 11.05.2025).
Assemblage Dataset [Jelektronnyj resurs]. URL: https://assemblage-dataset.net/ (data obrashhenija 11.05.2025).
MalwareDatabaseUnsorted [Jelektronnyj resurs]. URL: https://github.com/Pyran1/MalwareDatabaseUnsorted (data obrashhenija 11.05.2025).
Kalyan E.V.P. et al. Detection of malware using CNN. 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA). IEEE. 2022. P. 1-6.
Chaymae E.Y., Khalid C. Android malware detection through CNN ensemble learning on grayscale images. International Journal of Advanced Computer Science & Applications. 2025. V. 16. № 1.
Seneviratne S. et al. Self-supervised vision transformers for malware detection. IEEE Access. 2022. V. 10. P. 103121-103135.
Bavishi S., Modi S. Accelerating malware classification: a vision transformer solution. arXiv preprint arXiv:2409.19461. 2024.

[1] Exploits and vulnerabilities in Q1 2025 [Jelektronnyj resurs]. URL: https://securelist.com/vulnerabilities-and-exploits-in-q1-2025/116624/ (data obrashhenija 20.10.2025).

[2] Linux malware: types, families and trends [Jelektronnyj resurs]. URL: https://any.run/cybersecurity-blog/linux-malware-types-families-and-trends/ (data obrashhenija 20.10.2025).

[3] How to identify and remove linux malware infections [Jelektronnyj resurs]. URL: https://www.itprotoday.com/linux-os/how-to-identify-and-remove-linux-malware-infections (data obrashhenija 20.10.2025).

[4] What are indicators of compromise (IoC) [Jelektronnyj resurs]. URL: https://www.cloudflare.com/ru-ru/learning/security/what-are-indicators-of-compromise/ (data obrashhenija 20.10.2025).

[5] Onyebuchi O.B. Signature based network intrusion detection system using feature selection on android. Signature. 2020. V. 11. № 6. P. 551-558.

[6] Punyasiri D.L.S. Signature & behavior based malware detection. Malabe. Sri Lanka: Sri Lanka Institute of Information Technology. 2023.

[7] Sheluhin O.I., Rybakov S.Ju., Zvezhinskij S.S. Obnaruzhenie kiberatak i vredonosnogo programmnogo obespechenija nulevogo dnja metodami mashinnogo obuchenija. Radiotehnika. 2025. T. 89. № 8. S. 184-198. DOI: https://doi.org/10.18127/j00338486-202508-21 (in Russian).

[8] Qamar R., Zardari B.A. Artificial neural networks: an overview. Mesopotamian Journal of Computer Science. 2023. V. 2023. P. 124-133.

[9] Appalonov A.M., Maslennikova Ju.S., Sherstjukov O.N. Primenenie nejronnyh setej glubokogo obuchenija dlja analiza prostranstvennyh i vremennýh komponent razlozhenija polnogo jelektronnogo soderzhanija ionosfery. Radiotehnika. 2025. T. 89. № 1. S. 172-179. DOI: https://doi.org/10.18127/j00338486-202501-16 (in Russian).

[10] Malygin I.V., Bel'kov S.A., Mihajlik D.A., Stafeev K.V. Razrabotka metodov formirovanija obrazcov, obuchajushhih nej-ronnuju set' obnaruzhivat' i klassificirovat' pomehi v strukture poleznogo signala. Radiotehnika. 2024. T. 88. № 6. S. 121-129. DOI: 10.18127/j00338486-202406-15 (in Russian).

[11] Montesinos López O.A., Montesinos López A., Crossa J. Fundamentals of artificial neural networks and deep learning. Multivariate statistical machine learning methods for genomic prediction. Cham: Springer International Publishing. 2022. P. 379-425.

[12] A Brief introduction to recurrent neural networks [Jelektronnyj resurs]. URL: https://towardsdatascience.com/a-brief-introduction-to-recurrent-neural-networks-638f64a61ff4/ (data obrashhenija 11.05.2025).

[13] Taye M.M. Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation. 2023. V. 11. № 3. P. 52.

[14] Zhao X. et al. A review of convolutional neural networks in computer vision. Artificial Intelligence Review. 2024. V. 57. № 4. P. 99.

[15] Dosovitskiy A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. 2020.

[16] Zhang M. Neural attention: Enhancing qkv calculation in self-attention mechanism with neural networks. arXiv preprint arXiv:2310.11398. 2023.

[17] Bensaoud A., Kalita J. Deep multi-task learning for malware image classification. Journal of Information Security and Applications. 2022. V. 64. P. 103057.

[18] Katar O., Yıldırım O. Classification of Malware Images Using Fine-Tunned ViT. Sakarya University Journal of Computer and Information Sciences. 2024. V. 7. № 1. P. 22-35.

[19] Malware Bazaar Database [Jelektronnyj resurs]. URL: https://bazaar.abuse.ch/browse/tag/elf/ (data obrashhenija 11.05.2025).

[20] Labeled-Elfs [Jelektronnyj resurs]. URL: https://github.com/nimrodpar/Labeled-Elfs/tree/main (data obrashhenija 11.05.2025).

[21] Linux-malware [Jelektronnyj resurs]. URL: https://github.com/timb-machine/linux-malware/tree/main/malware/binaries (data obrashhenija 11.05.2025).

[22] Linux-Malware-Samples [Jelektronnyj resurs]. URL: https://github.com/MalwareSamples/Linux-Malware-Samples (data obrashhenija 11.05.2025).

[23] Assemblage Dataset [Jelektronnyj resurs]. URL: https://assemblage-dataset.net/ (data obrashhenija 11.05.2025).

[24] MalwareDatabaseUnsorted [Jelektronnyj resurs]. URL: https://github.com/Pyran1/MalwareDatabaseUnsorted (data obrashhenija 11.05.2025).

[25] Kalyan E.V.P. et al. Detection of malware using CNN. 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA). IEEE. 2022. P. 1-6.

[26] Chaymae E.Y., Khalid C. Android malware detection through CNN ensemble learning on grayscale images. International Journal of Advanced Computer Science & Applications. 2025. V. 16. № 1.

[27] Seneviratne S. et al. Self-supervised vision transformers for malware detection. IEEE Access. 2022. V. 10. P. 103121-103135.

[28] Bavishi S., Modi S. Accelerating malware classification: a vision transformer solution. arXiv preprint arXiv:2409.19461. 2024.

Abstract

How to cite

Related articles