Geodesic
Vulnerability analysis of neural networks in computer vision
Informacionnye tehnologii i vyčislitelnye sistemy, no. 4 (2023), pp. 49-58.

Voir la notice de l'article provenant de la source Math-Net.Ru

The work considers the actual problem of the vulnerability of artificial intelligence technologies based on neural networks. We show that the use of neural networks generates many vulnerabilities. We demonstrate specific examples of such vulnerabilities: incorrect classification of images containing adversarial noise or patches, failure of recognition systems in the presence of special patterns on the image, including those applied to objects in the real world, training data poisoning, etc. Based on the analysis, we show the need to improve the security of artificial intelligence technologies and suggest some considerations that contribute to this improvement.
Keywords: neural networks, attacks on neural networks, adversarial images, neural network security. 
@article{ITVS_2023_4_a5,
     author = {A. V. Trusov and E. E. Limonova and V. V. Arlazarov and A. A. Zatsarinnyi},
     title = {Vulnerability analysis of neural networks in computer vision},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {49--58},
     publisher = {mathdoc},
     number = {4},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2023_4_a5/}
}
TY  - JOUR
AU  - A. V. Trusov
AU  - E. E. Limonova
AU  - V. V. Arlazarov
AU  - A. A. Zatsarinnyi
TI  - Vulnerability analysis of neural networks in computer vision
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2023
SP  - 49
EP  - 58
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2023_4_a5/
LA  - ru
ID  - ITVS_2023_4_a5
ER  - 
%0 Journal Article
%A A. V. Trusov
%A E. E. Limonova
%A V. V. Arlazarov
%A A. A. Zatsarinnyi
%T Vulnerability analysis of neural networks in computer vision
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2023
%P 49-58
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2023_4_a5/
%G ru
%F ITVS_2023_4_a5
A. V. Trusov; E. E. Limonova; V. V. Arlazarov; A. A. Zatsarinnyi. Vulnerability analysis of neural networks in computer vision. Informacionnye tehnologii i vyčislitelnye sistemy, no. 4 (2023), pp. 49-58. http://geodesic.mathdoc.fr/item/ITVS_2023_4_a5/