Geodesic
Features of using Markov decision-making processes when modeling attacks on artificial intelligence systems
Vestnik Samarskogo universiteta. Estestvennonaučnaâ seriâ, Tome 30 (2024) no. 4, pp. 147-160 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

In this paper, we study the features of modeling attacks on artificial intelligence systems. Markov decision-making processes are used in the construction of the model. A multilevel approach to the interpretation of system states is proposed, which includes several stages of detailing the states. This approach is based on the MITRE ATLAS methodology and the FSTEC Threat Assessment Methodology. When forming the vector, the specifics of the intruder model are taken into account, and two main modeling modes are considered: on-time and off-time. The procedure for the formation of awards at the abstract level (without specifying the actions of the attacker) of building a model is described.
Keywords: network attack, vulnerability, Markov process, modeling, strategy, policy, teaching method. 
@article{VSGU_2024_30_4_a10,
     author = {I. A. Vetrov and V. V. Podtopelny},
     title = {Features of using {Markov} decision-making processes when modeling attacks on artificial intelligence systems},
     journal = {Vestnik Samarskogo universiteta. Estestvennonau\v{c}na\^a seri\^a},
     pages = {147--160},
     year = {2024},
     volume = {30},
     number = {4},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VSGU_2024_30_4_a10/}
}
TY  - JOUR
AU  - I. A. Vetrov
AU  - V. V. Podtopelny
TI  - Features of using Markov decision-making processes when modeling attacks on artificial intelligence systems
JO  - Vestnik Samarskogo universiteta. Estestvennonaučnaâ seriâ
PY  - 2024
SP  - 147
EP  - 160
VL  - 30
IS  - 4
UR  - http://geodesic.mathdoc.fr/item/VSGU_2024_30_4_a10/
LA  - ru
ID  - VSGU_2024_30_4_a10
ER  - 
%0 Journal Article
%A I. A. Vetrov
%A V. V. Podtopelny
%T Features of using Markov decision-making processes when modeling attacks on artificial intelligence systems
%J Vestnik Samarskogo universiteta. Estestvennonaučnaâ seriâ
%D 2024
%P 147-160
%V 30
%N 4
%U http://geodesic.mathdoc.fr/item/VSGU_2024_30_4_a10/
%G ru
%F VSGU_2024_30_4_a10
I. A. Vetrov; V. V. Podtopelny. Features of using Markov decision-making processes when modeling attacks on artificial intelligence systems. Vestnik Samarskogo universiteta. Estestvennonaučnaâ seriâ, Tome 30 (2024) no. 4, pp. 147-160. http://geodesic.mathdoc.fr/item/VSGU_2024_30_4_a10/

[1] Kotenko I.V., Saenko I.B., Lauta O.S., Vasilev N.A., Sadovnikov V.E., “Ataki i metody zaschity v sistemakh mashinnogo obucheniya: analiz sovremennykh issledovanii”, Voprosy kiberbezopasnosti, 2024, no. 1 (59), 24–37 | DOI | MR

[2] Namiot D.E., “Skhemy atak na modeli mashinnogo obucheniya”, International Journal of Open Information Technologies, 11:5 (2023), 68–86 https://cyberleninka.ru/article/n/shemy-atak-na-modeli-mashinnogo-obucheniya?ysclid=m5dmh9jnct363700583

[3] Xiaofan Zhou, Simon Yusuf Enoch, Dan Dong Seong Kim, “Markov Decision Process For Automatic Cyber Defense”, Information Security Applications, WISA 2022, Lecture Notes in Computer Science, 13720, eds. You I., Youn T.Y., Springer, Cham, 2023, 313–329 | DOI

[4] Booker L.B., Musman S.A., A Model-Based, Decision-Theoretic Perspective on Automated Cyber Response | DOI

[5] Zheng J., Namin A.S., “Defending SDN-based IoT Networks Against DDoS Attacks Using Markov Decision Process”, IEEE International Conference on Big Data (Big Data), 2018 | DOI

[6] Scheglov A.Yu., Zaschita kompyuternoi informatsii ot nesanktsionirovannogo dostupa, Nauka i Tekhnika, Sankt-Peterburg, 2004, 384 pp. https://reallib.org/reader?file=523140

[7] Kokhenderfer M., Uiler T., Rei K., Algoritmy prinyatiya reshenii, per. s angl. V.S. Yatsenkova, DMK Press, M., 2023, 684 pp. https://znanium.ru/catalog/document?id=445338

[8] Metodicheskii dokument. Metodika otsenki ugroz bezopasnosti informatsii, utv. Federalnoi sluzhboi po tekhnicheskomu i eksportnomu kontrolyu 5 fevralya 2021 g., M., 2021, 83 pp. https://fstec.ru/dokumenty/vse-dokumenty/spetsialnye-normativnye-dokumenty/metodicheskij-dokument-ot-5-fevralya-2021-g

[9] MITRE ATLAS, , MITRE ATT (data obrascheniya: 02.05.2024) https://atlas.mitre.org

[10] Gorbachev I.E., Glukhov A.P., “Modelirovanie protsessov narusheniya informatsionnoi bezopasnosti kriticheskoi infrastruktury”, Trudy SPIIRAN, 2015, no. 1 (38), 112–135 | DOI

[11] Faranak Abri, Jianjun Zheng, Akbar Siami Namin, Keith S. Jones, “Markov Decision Process for Modeling Social Engineering Attacks and Finding Optimal Attack Strategies”, IEEE Access, 10 (2022), 109949–109968 | DOI

[12] Goryunov M.N., Matskevich A.G., Rybolovlev D.A., “Sintez modeli mashinnogo obucheniya dlya obnaruzheniya kompyuternykh atak na osnove nabora dannykh CICIDS2017”, Trudy instituta sistemnogo programmirovaniya RAN, 32:5 (2020), 81–94 | DOI

[13] Goryunov M.N., Rybolovlev A.A., Rybolovlev D.A., “Otsenka primenimosti metodov mashinnogo obucheniya dlya obnaruzheniya kompyuternykh atak”, Informatsionnye sistemy i tekhnologii, 2020, no. 6 (122), 103–111