Razornet: Adversarial training and noise training on a deep neural network fooled by a shallow neural network

Razornet: Adversarial training and noise training on a deep neural network fooled by a shallow neural network

In this work, we propose ShallowDeepNet, a novel system architecture that includes a shallow and a deep neural network. The shallow neural network has the duty of data preprocessing and generating adversarial samples. The deep neural network has the duty of understanding data and information as well...

Full description

Bibliographic Details
Main Authors: Salem, M. (Author), Taheri, S. (Author), Yuan, J.-S (Author)
Format: Article
Language:English
Published: MDPI AG 2019
Subjects:
Adversarial attacks
Adversarial perturbations
Adversarial training
Biometric recognition
Convolutional neural networks
Data security
Deep learning
Multiple subnetwork
Noise training
Pill recognition
Transfer learning
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items