Image Super-Resolution as a Defense Against Adversarial Attacks

by   Aamir Mustafa, et al.

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human imperceptible adversarial noise patterns which constrain their deployment in critical security-sensitive systems. This paper proposes a computationally efficient image enhancement approach that provides a strong defense mechanism to effectively mitigate the effect of such adversarial perturbations. We show that the deep image restoration networks learn mapping functions that can bring off-the-manifold adversarial samples onto the natural image manifold, thus restoring classifier beliefs towards correct classes. A distinguishing feature of our approach is that, in addition to providing robustness against attacks, it simultaneously enhances image quality and retains models performance on clean images. Furthermore, the proposed method does not modify the classifier or requires a separate mechanism to detect adversarial images. The effectiveness of the scheme has been demonstrated through extensive experiments, where it has proven a strong defense in both white-box and black-box attack settings. The proposed scheme is simple and has the following advantages: (1) it does not require any model training or parameter optimization, (2) it complements other existing defense mechanisms, (3) it is agnostic to the attacked model and attack type and (4) it provides superior performance across all popular attack algorithms. Our codes are publicly available at


page 4

page 5

page 11

page 12


Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models

In recent years, deep neural network approaches have been widely adopted...

Enhanced countering adversarial attacks via input denoising and feature restoring

Despite the fact that deep neural networks (DNNs) have achieved prominen...

Open-set Adversarial Defense

Open-set recognition and adversarial defense study two key aspects of de...

Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks

Deep neural networks (DNNs) have been enormously successful across a var...

Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge

Autonomous systems are highly vulnerable to a variety of adversarial att...

Open-set Adversarial Defense with Clean-Adversarial Mutual Learning

Open-set recognition and adversarial defense study two key aspects of de...

Fashion-Guided Adversarial Attack on Person Segmentation

This paper presents the first adversarial example based method for attac...

Please sign up or login with your details

Forgot password? Click here to reset