Boosting Adversarial Attacks on Neural Networks with Better Optimizer

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence poses potential security threats to deep learning systems....

Full description

Bibliographic Details

Published in:	Security and communication networks Vol. 2021; pp. 1 - 9
Main Authors:	Yin, Heng, Zhang, Hengwei, Wang, Jindong, Dou, Ruiyu
Format:	Journal Article
Language:	English
Published:	London Hindawi 07.06.2021 John Wiley & Sons, Inc
Subjects:	Algorithms Artificial neural networks Iterative methods Machine learning Methods Neural networks Object recognition Optimization
ISSN:	1939-0114, 1939-0122
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!