A decade of adversarial examples: a survey on the nature and understanding of neural network non-robustness

• Published in: Kompʹûternaâ optika Vol. 49; no. 2; pp. 222 - 252
• Main Authors: Trusov, A.V., Limonova, E.E., Arlazarov, V.V.
• Format: Journal Article
• Language: English
• Published: Samara National Research University 01.04.2025
• Subjects: adversarial deep learning; adversarial examples; neural network security; neural networks
• ISSN: 0134-2452; 2412-6179
• DOI: 10.18287/2412-6179-CO-1494

Adversarial examples, in the context of computer vision, are inputs deliberately crafted to deceive or mislead artificial neural networks. These examples exploit vulnerabilities in neural networks, resulting in minimal alterations to the original input that are imperceptible by humans but can signif...