Systems and Means of Informatics
2024, Volume 34, Issue 1, pp pp 80-91
THE LIFECYCLE OF CYBERATTACKS ON MACHINE LEARNING SYSTEM VULNERABILITIES
Abstract
The article discusses the problems of ensuring the necessary level of information security of artificial intelligence systems which is becoming one of the key factors in their widespread use. Based on the analysis of data on committed cyberattacks on well-known machine learning systems (MLS), a complete set of stages of the life cycle of computer attacks on MLS was formed, target MLS vulnerabilities for each stage of the life cycle were determined, methods of attacks on MLS vulnerabilities were systematized, and approaches to ensuring information security of the system were outlined.
[+] References (6)
- MITRE ATT&CK. Available at: https://attack.mitre.org (accessed February 20, 2024).
- MITRE ATLAS™ (Adversarial Threat Landscape for Artificial-Intelligence Systems). Available at: https://atlas.securityhub.ru (accessed February 20, 2024).
- Universitet ITMO [ITMO University]. Available at: https://itmo.ru/?ysclid= lqbyvy76bx557068225 (accessed February 20, 2024).
- Microsoft rasskazala, kak khakery izbezhali obnaruzheniya pri atake SolarWinds [Microsoft told how hackers evaded detection in the SolarWinds attack]. Available at: https://habr.com/ru/news/538476/ (accessed February 20, 2024).
- Zatsarinnyy, A. A., and A. P. Suchkov. 2023. Nekotorye podkhody k analizu faktorov, vliyayushchikh na informatsionnuyu bezopasnost' sistem iskusstvennogo intellekta [Some approaches to the analysis of factors affecting the information security of artificial intelligence systems]. Sistemy i Sredstva Informatiki - Systems and Means of Informatics 33(3):95-107. doi: 10.14357/08696527230308. EDN: QNXZBN.
- Gavrilov, V.E., and A. A. Zatsarinnyy. 2020. Issledovanie problem normativno- metodicheskogo regulirovaniya v oblasti informatsionnoy bezopasnosti protsessov sozda- niya i vnedreniya informatsionnykh tekhnologiy, razrabatyvaemykh v ramkakh program- my "Tsifrovaya ekonomika" [Study of the problems of normative-methodical management in the field of information security processes for the creation and implementation of information technologies developed in the framework of the "Digital economy"]. Vestnik Voronezhskogo instituta FSIN Rossii [Bulletin of the Voronezh Institute of the Federal Penitentiary Service of Russia] 3:30-37.
[+] About this article
Title
THE LIFECYCLE OF CYBERATTACKS ON MACHINE LEARNING SYSTEM VULNERABILITIES
Journal
Systems and Means of Informatics
Volume 34, Issue 1, pp 80-91
Cover Date
2024-04-10
DOI
10.14357/08696527240107
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
information security; artificial intelligence systems; machine learning; types of information protection
Authors
A. P. Suchkov 
Author Affiliations
Federal Research Center "Computer Science and Control", Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|