Method of adaptation of the deep neural network to the recognition of computer viruses

  • L. Tereykovskaya Kyiv National University of Civil Engineering and Architecture
  • Ye. Ivanchenko Kyiv National University of Civil Engineering and Architecture
  • V. Pogorelov National Aviation University
Keywords: malware, intrusion detection system, cyberattack, deobfuscation procedure, DNN architecture adaptation method.


The analysis of scientific and applied researches devoted to creation of the systems of protection against harmful software shows that one of the most perspective directions of development of the systems of recognition of malicious software is the improvement of their mathematical support due to the application of modern neural network models on the basis of deep neural networks. The results of the analysis also identified the need to create a method for developing the architecture of deep neural network adapted to the conditions of use in modern means of recognition. In the course of research, a method for developing a deep neural network architecture designed to detect malicious software was proposed. In contrast to the existing methods, this method allows avoiding during the development of a neural network model of long-term numerical experiments aimed at determining the appropriateness of its application and optimizing its structural parameters. Through numerical experiments using computer virus database BIG-2015 published by Microsoft, it is shown that the method allows building a neural network model that provides a recognition error that is commensurate with the error of modern computer virus recognition systems. Prospects for further research are related to the adaptation of the proposed method to the application of deep neural networks in behavioural analyzers.


Neyrosetevye modeli, metody i sredstva otsenki parametrov bezopasnosti Internet-oriyentirovШНМykh informatsionnykh system / A. Korchenko, I. Tereykovskiy, N. Karpinskiy [et al.]. Kiev: TOV «Nash Format», 2016. – 275 p.

Development of the intelligent decision-making support system to manage cyber protection at the object of informatization / V. Lakhno,Y. Boiko, A. Mishchenko, V. Kozlovskii, [et al.] // Eastern-European Journal of Enterprise Technologies. – 2017. – Vol. 2, Iss. 9 (86). – P. 53–61.

Lakhno V. Creation of the adaptive cyber threat detection system on the basis of fuzzy feature clustering / V. Lakhno // Eastern-European Journal of Enterprise Technologies. – 2016. – Vol. 2, Iss. 9 (80). – P. 18–25.

Novel feature extraction, selection and fusion for effective malware family classification / M. Ahmadi, D. Ulyanov, S. Semenov [et al.] // Proceedings of the Sixth ACM Conference on Data and Application Security and Privacy. – New York : ACM, 2016. – P. 183-194.

Omotayo F. A. Dlamini and Jonathan M. Blackledge Asiru. Application of Artificial Intelligence for Detecting Derived Viruses / F. A. Omotayo, T. Moses // 16th European Conference on Cyber Warfare and Security (ECCWS 2017) (Dublin 2017 June 29-30). – University College Dublin. – P. 217-227.

Rudenko O.H., Bodianskyi Ye. Shtuchni neironni merezhi. – Kharkiv : «Kompaniia SMIT», 2016. – 404 p.

Encoding of neural network model exit signal, that is devoted for distinction of graphical images in biometric authenticate systems / L.Tereykovska, I.Tereykovskiy, E. Aytkhozhaeva // News of the National Academy of Sciences of the Republic of Kazakhstan, Series of Geology and Technical Sciences. – 2017, Vol. 6, No. 426, P. 217 – 224.

Determination of structural parameters of multilayer perceptron designed to estimate parameters of technical systems / Z. Hu, I. A. Tereykovskiy, L. O. Tereykovska [et al.] // International Journal of Intelligent Systems and Applications. – 2017. – Vol 9. – No.10.P.57-62

Abstract views: 1
PDF Downloads: 3
How to Cite
Tereykovskaya, L., Ivanchenko, Y., & Pogorelov, V. (2020). Method of adaptation of the deep neural network to the recognition of computer viruses. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (35), 198-205. Retrieved from
Computer science and computer engineering