TwinNet: A Double Sub-Network Framework for Detecting Universal Adversarial Perturbations

TwinNet: A Double Sub-Network Framework for Detecting Universal Adversarial Perturbations

Deep neural network has achieved great progress on tasks involving complex abstract concepts. However, there exist adversarial perturbations, which are imperceptible to humans, which can tremendously undermine the performance of deep neural network classifiers. Moreover, universal adversarial pertur...

Full description

Bibliographic Details
Main Authors: Yibin Ruan, Jiazhu Dai
Format: Article
Language:English
Published: MDPI AG 2018-03-01
Series:Future Internet
Subjects:
deep neural network
universal adversarial perturbation
double sub-network
detecting
PCA
ImageNet
Online Access:http://www.mdpi.com/1999-5903/10/3/26

Internet

http://www.mdpi.com/1999-5903/10/3/26

Similar Items