RGN-Defense: erasing adversarial perturbations using deep residual generative network

Weiqi Fan; Guangling Sun; Xiaobao Deng

doi:10.1117/1.JEI.28.1.013027

7 February 2019 RGN-Defense: erasing adversarial perturbations using deep residual generative network

Weiqi Fan, Guangling Sun, Xiaobao Deng

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 1, 013027 (February 2019). https://doi.org/10.1117/1.JEI.28.1.013027

Abstract

In recent years, deep neural networks have achieved great success in various fields, especially in computer vision. However, recent investigations have shown that current state-of-the-art classification models are highly vulnerable to adversarial perturbations contained in the input examples. Therefore, we propose a defense methodology against the adversarial perturbations. Prior to a targeted network, adversarial perturbations are erased or mitigated via a deep residual generative network (RGN). Through adopting an auxiliary network VGG-19, the RGN is trained toward optimization of a joint loss, including low-level pixel loss, middle-level texture loss, and high-level task loss, thereby the restored examples are highly consistent with the original legitimate examples. We call our proposed defense based on RGN as RGN-Defense. It is an independent defense module that can be flexibly integrated with other defense strategy, for example, adversarial training, to construct a more powerful defense system. In the experiment, we evaluate our approach on ImageNet, and the comprehensive results have demonstrated robustness of RGN-Defense against current representative attacks.

Citation Download Citation

Weiqi Fan, Guangling Sun, and Xiaobao Deng "RGN-Defense: erasing adversarial perturbations using deep residual generative network," Journal of Electronic Imaging 28(1), 013027 (7 February 2019). https://doi.org/10.1117/1.JEI.28.1.013027

Received: 18 August 2018; Accepted: 3 January 2019; Published: 7 February 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available