Adversarial ink: componentwise backward error attacks on deep learning (2023)
Attributed to:
Mathematics of Adversarial Attacks
funded by
EPSRC
Abstract
No abstract provided
Bibliographic Information
Digital Object Identifier: http://dx.doi.org/10.1093/imamat/hxad017
Publication URI: http://dx.doi.org/10.1093/imamat/hxad017
Type: Journal Article/Review
Parent Publication: IMA Journal of Applied Mathematics