|
Specific features of ensuring the functional safety of automated systems using artificial intelligence technology
V. E. Gavrilov, A. A. Zatsarinny Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119133, Russian Federation
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.
Keywords:
artificial intelligence systems, information technology security, functional security, software quality, attacks, information protection.
Received: 15.06.2024
Citation:
V. E. Gavrilov, A. A. Zatsarinny, “Specific features of ensuring the functional safety of automated systems using artificial intelligence technology”, Sistemy i Sredstva Inform., 34:3 (2024), 23–34
Linking options:
https://www.mathnet.ru/eng/ssi943 https://www.mathnet.ru/eng/ssi/v34/i3/p23
|
|