Defense Against Adversarial Attacks in Deep Learning

Defense Against Adversarial Attacks in Deep Learning

Neural networks are very vulnerable to adversarial examples, which threaten their application in security systems, such as face recognition, and autopilot. In response to this problem, we propose a new defensive strategy. In our strategy, we propose a new deep denoising neural network, which is call...

Full description

Bibliographic Details
Main Authors: Yuancheng Li, Yimeng Wang
Format: Article
Language:English
Published: MDPI AG 2018-12-01
Series:Applied Sciences
Subjects:
adversarial attacks
deep learning
face recognition
Wasserstein generative adversarial networks (W-GAN)
denoiser
knowledge transfer
Online Access:http://www.mdpi.com/2076-3417/9/1/76

Internet

http://www.mdpi.com/2076-3417/9/1/76

Similar Items