Adversarial detection by approximation of ensemble boundary

Despite being effective in many application areas, Deep Neural Networks (DNNs) are vulnerable to being attacked. In object recognition, the attack takes the form of a small perturbation added to an image, that causes the DNN to misclassify, but to a human appears no different. Adversarial attacks le...

Full description

Bibliographic Details

Published in:	Neurocomputing (Amsterdam) Vol. 622; p. 129364
Main Author:	Windeatt, Terry
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 14.03.2025
Subjects:	Adversarial robustness Boolean functions Deep neural networks Ensemble Machine learning Security Boolean functions Adversarial robustness Deep neural networks Security Ensemble Machine learning
ISSN:	0925-2312
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!