Analysis of the vulnerability of YOLO neural network models to the Fast Sign Gradient Method attack

The analysis of formalized conditions for creating universal images falsely classified by computer vision algorithms, called adversarial examples, on YOLO neural network models is presented. The pattern of successful creation of a universal destructive image depending on the generated dataset on whi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Nauchno-tekhnicheskiĭ vestnik informat͡s︡ionnykh tekhnologiĭ, mekhaniki i optiki Ročník 24; číslo 6; s. 1066 - 1070
Hlavní autoři: Teterev, N.V., Trifonov, V.E., Levina, A.B.
Médium: Journal Article
Jazyk:angličtina
Vydáno: ITMO University 01.12.2024
Témata:
coco
yolo
генеративные атаки
набор данных
нейронная сеть
состязательный пример
ISSN:2226-1494, 2500-0373
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The analysis of formalized conditions for creating universal images falsely classified by computer vision algorithms, called adversarial examples, on YOLO neural network models is presented. The pattern of successful creation of a universal destructive image depending on the generated dataset on which neural networks were trained using the Fast Sign Gradient Method attack is identified and studied. The specified pattern is demonstrated for YOLO8, YOLO9, YOLO10, YOLO11 classifier models trained on the standard COCO dataset.
ISSN:2226-1494
2500-0373
DOI:10.17586/2226-1494-2024-24-6-1066-1070