Stylized Adversarial Defense

07/29/2020
by   Muzammal Naseer, et al.
8

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to robustify the model. In contrast to existing adversarial training methods that only use class-boundary information (e.g., using a cross entropy loss), we propose to exploit additional information from the feature space to craft stronger adversaries that are in turn used to learn a robust model. Specifically, we use the style and content information of the target sample from another class, alongside its class boundary information to create adversarial perturbations. We apply our proposed multi-task objective in a deeply supervised manner, extracting multi-scale feature knowledge to create maximally separating adversaries. Subsequently, we propose a max-margin adversarial training approach that minimizes the distance between source image and its adversary and maximizes the distance between the adversary and the target image. Our adversarial training approach demonstrates strong robustness compared to state of the art defenses, generalizes well to naturally occurring corruptions and data distributional shifts, and retains the model accuracy on clean examples.

READ FULL TEXT

page 2

page 3

page 5

page 7

page 8

10/09/2019

Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system

Adversarial training, in which a network is trained on both adversarial ...
05/15/2020

Initializing Perturbations in Multiple Directions for Fast Adversarial Training

Recent developments in the filed of Deep Learning have demonstrated that...
06/08/2018

Monge beats Bayes: Hardness Results for Adversarial Training

The last few years have seen extensive empirical study of the robustness...
03/02/2022

Enhancing Adversarial Robustness for Deep Metric Learning

Owing to security implications of adversarial vulnerability, adversarial...
10/20/2020

Towards Understanding the Dynamics of the First-Order Adversaries

An acknowledged weakness of neural networks is their vulnerability to ad...
05/02/2019

You Only Propagate Once: Painless Adversarial Training Using Maximal Principle

Deep learning achieves state-of-the-art results in many areas. However r...
11/25/2021

Going Grayscale: The Road to Understanding and Improving Unlearnable Examples

Recent work has shown that imperceptible perturbations can be applied to...

Code Repositories

SAT

Official repository for "Stylized Adversarial Training" (2020)


view repo