Work

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

Year: 2024

Type: article

Abstract: 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.

Source: Scientific and technical journal of information technologies mechanics and optics

DOI: 10.17586/2226-1494-2024-24-6-1066-1070

Authors: N.V. Teterev, V.E. Trifonov, A.B. Levina

Institution: Saint Petersburg State Electrotechnical University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: Ministry of Science and Higher Education of the Russian Federation

OpenAlex ID: W4406678492