Adversarial Dual Network Learning With Randomized Image Transform for Restoring Attacked Images

Adversarial Dual Network Learning With Randomized Image Transform for Restoring Attacked Images

We develop a new method for defending deep neural networks against attacks using adversarial dual network learning with randomized nonlinear image transform. We introduce a randomized nonlinear transform to disturb and partially destroy the sophisticated pattern of attack noise. We then design a gen...

Full description

Bibliographic Details
Main Authors: Jianhe Yuan, Zhihai He
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Adversarial attack
adversarial defense
deep neural network
Online Access:https://ieeexplore.ieee.org/document/8968395/

Internet

https://ieeexplore.ieee.org/document/8968395/

Similar Items