Systems and Means of Informatics
2024, Volume 34, Issue 3, pp 23-34
SPECIFIC FEATURES OF ENSURING THE FUNCTIONAL SAFETY OF AUTOMATED SYSTEMS USING ARTIFICIAL INTELLIGENCE TECHNOLOGY
- V. E. Gavrilov
- A. A. Zatsarinny
Abstract
The article is devoted to the consideration of the features of ensuring the functional safety of automated systems both with and without the use of artificial intelligence technology. The factors affecting the quality of functional software in both cases are compared. It is shown that most of the attacks specific to artificial intelligence systems are blocked by standard means of protecting information from unauthorized access. The effectiveness of protection against an evasion attack is determined by the quality of the artificial intelligence system and the data used for training. For automated systems without the use of artificial intelligence technology, evasion attacks are also relevant and the effectiveness of protection against them is determined by the quality of functional software.
[+] References (21)
- Gavrilov, V. E., and A. A. Zatsarinny. 2022. Problemyi ugrozy vnedreniya nekotorykh novykh tsifrovykh tekhnologiy [Problems and threats of some new digital technologies implementation]. Sistemy i Sredstva Informatiki — Systems and Means of Informatics 32(3):15{25. doi: 10.14357/08696527220302. EDN: QKESJR.
- GOST R 50.1.053-2005. 2005. Informatsionnye tekhnologii. Osnovnye terminy i opredeleniya v oblasti tekhnicheskoy zashchity informatsii [Information technologies. Basic terms and definitions in scope of technical protection of information]. Moscow: Stan- dardinform Publs. 16 p.
- GOST R MEK 62061-2015. 2016. Funktsional’naya bezopasnost’ sistem elektricheskikh, elektronnykh, programmiruemykh elektronnykh, svyazannykh s bezopasnost’yu [Safety of machinery. Functional safety of safety-related electrical, electronic, and programmable electronic control systems]. Moscow: Standardinform Publs. 78 p.
- Gavrilov, V.E., and A. A. Zatsarinny. 2018. Nekotorye sistemotekhnicheskie voprosy ispol’zovaniya intellektual’nogo analiza dannykh dlya obespecheniya zashchity informatsii v situatsionnykh tsentrakh [Regarding systemic and technical problems of applying intellectual data analysis for providing information protection in situational centers]. Sistemy i Sredstva Informatiki — Systems and Means of Informatics 28(1):89{98. doi: 10.14357/08696527180107. EDN: YVXNEH.
- Zatsarinny, 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):95407. doi: 10.14357/08696527230308.EDN: QNXZBN.
- Natsional’naya strategiya razvitiya iskusstvennogo intellekta na period do 2030 goda: Ukaz Prezidenta RF ot 10 oktyabrya 2019 g. No. 490 “O razvitii iskusstvennogo intellekta v Rossiyskoy Federatsii” [National strategy for the development of artificial intelligence for the period up to 2030: Decree of the President of the Russian Federation No. 490 “On the development of artificial intelligence in the Russian Federation” dated 10.10.2019].
- Smolin, D. V. 2004. Vvedenie v iskusstvennyy intellekt: Konspekt lektsiy [Introduction to artificial intelligence: Lecture notes]. Moscow: Fizmatlit. 15-17.
- GOST R 59276-2020. 2005. Sistemy iskusstvennogo intellekta. Sposoby obespecheniya doveriya. Obshchie polozheniya [Artificial intelligence systems. Methods for ensuring trust. General]. Moscow: Standardinform Publs. 16 p.
- GOST 28195-89. 1989. Otsenka kachestva programmnykh sredstv. Obshchie polozheniya [Quality control of software systems. General principles]. Moscow: Standards Publs. 31 p.
- GOST R 56939-2016. 2018. Zashchita informatsii. Razrabotka bezopasnogo programmnogo obespecheniya. Obshchie trebovaniya [Information protection. Secure software development. General requirements]. Moscow: Standardinform Publs. 24 p.
- GOST R 59793-2021. 2021. Informatsionnye tekhnologii. Kompleks standartov na avtomatizirovannye sistemy. Avtomatizirovannye sistemy. Stadii sozdaniya [Information technology. Set of standards for automated systems. Stages of development]. Moscow: Standardinform Publs. 8 p.
- Zatsarinny, A. A., and Yu. S. Ionenkov. 2022. Nekotorye voprosy otsenki vnutrennego kachestva informatsionnykh sistem [Some issues of internal quality assessment of information systems]. Sistemy i Sredstva Informatiki — Systems and Means of Informatics 32(1):63{72. doi: 10.14357/08696527220106. EDN: NULTQH.
- GOST R 59898-2021. 2021. Otsenka kachestva sistem iskusstvennogo intellekta. Obshchie polozheniya [Quality assurance of artificial intelligence systems. General]. Moscow: Russian Standardization Institute. 24 p.
- FSTEC Rossii. June 2, 2020. Trebovaniya po bezopasnosti informatsii, ustanavlivayushchie urovni doveriya k sredstvam tekhnicheskoy zashchity informatsii i sredstvam obespecheniya bezopasnosti informatsionnykh tekhnologiy: Prikaz No. 76 [Information security requirements establishing levels of trust in technical information protection tools and information technology security tools: Order No. 76]. 17 p.
- Vassilev, A., A. Oprea, A. Fordyce, and H. Anderson. 2024. Adversarial machine learning: A taxonomy and terminology of attacks and mitigations. Gaithersburg, MD: National Institute of Standards and Technology. NIST Artifcial Intelligence (AI) Report, NIST Trustworthy and Responsible AI. NIST AI 100-2e2023. 107 p. doi: 10.6028/NIST.AT100-2e2023.
- NIST. 25.08.2007. FIPS PUB 140-2. Security requirements for cryptographic modules. Available at: https://nvlpubs.nist.gov/nistpubs/FIPS/NIST.FIPS.140-2.pdf (accessed August 27, 2024).
- ISO/IEC 5259-2. Artificial intelligence — Data quality for analytics and machine learning (ML). Part 2: Data quality measures.
- Zatsarinny, A. A., and Yu. S. Ionenkov. 2022. O primenenii ekspertnykh metodov pri otsenke effektivnosti i kachestva informatsionnykh sistem [On the use of expert methods in evaluating effectiveness and quality of information systems]. Sistemy i Sredstva Informatiki — Systems and Means of Informatics 32(2):47{57. doi:
10.14357/08696527220205. EDN: NJDPAY.
- Gavrilov, V.E., and A. A. Zatsarinny. 2016. Nekotorye sistemotekhnicheskie i normativno-metodicheskie voprosy obespecheniya zashchity informatsii v avtomatizirovannykh informatsionnykh sistemakh na oblachnykh tekhnologiyakh s ispol’zovaniem metodov iskusstvennogo intellekta [On system-technical and regulatory-methodological problems of data security in cloud automated information systems using artificial intelligence technologies]. Sistemy i Sredstva Informatiki — Systems and Means of Informatics 26(4):38{50. doi: 10.14357/08696527160404. EDN: XAKZBF.
- Garbuk, S. V. 2024. Funktsional’nost’ i bezopasnost’ sistem iskusstvennogo intellekta: kachestvo dannykh [Functionality and security of artificial intelligence systems: Data quality]. Otkrytye sistemy. SUBD [Open Systems. DBMS] 1:18-22. doi: 10.51793/OS.2024.95.90.004. EDN: IKAMSA.
- GOST R 59921.7-2022. 2021. Sistemy iskusstvennogo intellekta v klinicheskoy meditsine. Algoritmy analiza meditsinskikh izobrazheniy. Metody ispytaniy. Obshchie trebovaniya [Artificial intelligence systems in clinical medicine. Algorithms of medical images analysis. Test methods. General requirements]. Moscow: Russian Standardization Institute. 36 p.
[+] About this article
Title
SPECIFIC FEATURES OF ENSURING THE FUNCTIONAL SAFETY OF AUTOMATED SYSTEMS USING ARTIFICIAL INTELLIGENCE TECHNOLOGY
Journal
Systems and Means of Informatics
Volume 34, Issue 3, pp 23-34
Cover Date
2024-10-30
DOI
10.14357/08696527240303
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
artificial intelligence systems; information technology security; functional security; software quality; attacks; information protection
Authors
V. E. Gavrilov and A. A. Zatsarinny
Author Affiliations
Federal Research Center "Computer Science and Control", Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|