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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nauchno-tekhnicheskiĭ vestnik informat͡s︡ionnykh tekhnologiĭ, mekhaniki i optiki Jg. 24; H. 6; S. 1066 - 1070
Hauptverfasser: Teterev, N.V., Trifonov, V.E., Levina, A.B.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: ITMO University 01.12.2024
Schlagworte:
coco
yolo
генеративные атаки
набор данных
нейронная сеть
состязательный пример
ISSN:2226-1494, 2500-0373
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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