Proceedings of TUSUR University / Archive / Issue of Journal № 2, t. 27, 2024 / Features of modeling the attacks on the machine learning model using Markov decision-making processes

Features of modeling the attacks on the machine learning model using Markov decision-making processes

DOI: 10.21293/1818-0442-2024-27-2-21-30

Download article in PDF format

JATS xml

Abstract: The issues that arise when determining the problem of modeling the impact on artificial intelligence models that are integrated into the network infrastructure are considered. Various research methods are presented and characterized, including the MITER methodology used in constructing the network impact vector. The features of using Markov decision-making processes in modeling attack influences are considered. Their significance for various procedures for determining vector parameters is considered. When constructing the modeling specifics, the au-thors take into account the features of determining the vulnera-bilities of artificial intelligence systems. The vector impact of major exploits of vulnerabilities is being studied.

Keywords: network attack, vulnerability, markov process modeling, strategy, policy, teaching method, artificial intelligence

For citation:
Podtopelnyy V. V. Features of modeling the attacks on the machine learning model using Markov decision-making processes. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2024, vol. 27, no. 2, pp. 21–30. DOI: 10.21293/1818-0442-2024-27-2-21-30

Authors and copyright holders:

Podtopelnyy V. V. , Kaliningrad State Technical University (Kaliningrad, Russia)

1. Metodicheskij dokument «Metodika ocenki ugroz bezopasnosti informacii» (utv. Federalnoj sluzhboj po tehnicheskomu i eksportnomu kontrolyu 5 fevralya 2021 g.). 83 p. Available at: https://fstec.ru/dokumenty/vse-dokumenty/spetsialnye-normativnye-dokumenty/metodicheskij-dokument-ot-5-fevralya-2021-g, free (Accessed: July 25, 2024).
2. MITRA ATLAS // MITRA ATLANT Available at: https://atlas.mitre.org, free (Accessed: May 02, 2024).
3. Namiotsky D.E. [Shemy atak na modeli mashinnogo obucheniya]. International Journal of Open Information Technologies, 2023, vol. 11, no. 5, pp. 68–86 (in Russ.).
4. Xiaofan Zhou, Simon Yusuf Enoch, Dan Dong Song Kim. Markov decision-making process for automatic cyberbullying (WISA 2023). Available at: https://arxiv.org/abs/2207.05436, free (Accessed: May 13, 2024).
5. Booker L.B., Musman S.A. A model-based view of automated implementation in cyberspace based on the theory of decision-making. Available at: https://arxiv.org/abs/2002.08957, free (Accessed: May 13, 2024).
6. Zheng J., Namin A.S. [Protection of the Internet of Things based on SDN from DDoS attacks using the Markov decision-making process]. Proceedings of the IEEE International Conference on Big Data 2018, Big Data–2018. 2018, pp. 4589–4592.
7. Kohenderfer M., Wheeler T., Ray K. At the decision-making algorithm. M.: DMK-Press, 2023, 684 p. (in Russ.).
8. Sutton R.S., Barto E.J. Algoritmy prinyatiya reshenij. Engagement with reinforcement: An introduction. 2nd ed. Moscow, DMK-Press, 2020, 552 p.
9. Mazengia D.H. Forecasting prices in the electricity market using time series models: dissertation for the degree of Master of Science in the field of electric power engineering. Gothenburg, Chalmers University of Technology, 2008, 89 p.
10. General descriptions and classifications of attack patterns Available at: https://capec.mitre.org, free (Accessed: May 12, 2024).
11. Calculator of the general capability assessment system Available at: https://nvd.nist.gov/vuln-metrics/cvss/v2-calculator, free (Accessed: May 13, 2024).