Stylized Adversarial Defense

Authors

Muzammal Naseer, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Salman Khan, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Munawar Hayat, Monash University
Fahad Shahbaz Khan, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Fatih Porikli, Qualcomm Incorporated

Document Type

Article

Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

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's accuracy on clean examples.

First Page

1

Last Page

12

DOI

10.1109/TPAMI.2022.3207917

Publication Date

9-19-2022

Keywords

Adversarial attacks, adversarial training, Computational modeling, max-margin learning, multi-task objective, Multitasking, Perturbation methods, Predictive models, Robustness, style transfer, Training, Visualization

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

M. Naseer, S. Khan, M. Hayat, F. S. Khan and F. Porikli, "Stylized Adversarial Defense," in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, doi: 10.1109/TPAMI.2022.3207917.