DVAE-SR: denoiser variational auto-encoder and super-resolution to counter adversarial attacks

Omar Dardour; Mourad Zaied; Petia Radeva

doi:10.1117/12.2586949

4 January 2021 DVAE-SR: denoiser variational auto-encoder and super-resolution to counter adversarial attacks

Omar Dardour, Mourad Zaied, Petia Radeva

Proceedings Volume 11605, Thirteenth International Conference on Machine Vision; 1160522 (2021) https://doi.org/10.1117/12.2586949
Event: Thirteenth International Conference on Machine Vision, 2020, Rome, Italy

Abstract

Recently, adversarial examples become one of the most dangerous risks in deep learning, which affects applications of real world such as robotics, cyber-security and computer vision. In image classification, adversarial attacks showed the ability to fool classifiers with small imperceptible perturbations added to the input. In this paper, we present an efficient defense mechanism, we call DVAE-SR that combine variational autoencoder and super-resolution to eliminate adversarial perturbation from image input before feeding it to the CNN classifier. The DVAE-SR can successfully defend against both white-box and black-box attacks without retraining CNN classifier and it recovers better accuracy than Defense-GAN and Defense-VAE.

Citation Download Citation

Omar Dardour, Mourad Zaied, and Petia Radeva "DVAE-SR: denoiser variational auto-encoder and super-resolution to counter adversarial attacks", Proc. SPIE 11605, Thirteenth International Conference on Machine Vision, 1160522 (4 January 2021); https://doi.org/10.1117/12.2586949

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