English

Stylized Adversarial Defense

Computer Vision and Pattern Recognition 2022-09-19 v2

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 accuracy on clean examples.

Keywords

Cite

@article{arxiv.2007.14672,
  title  = {Stylized Adversarial Defense},
  author = {Muzammal Naseer and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Fatih Porikli},
  journal= {arXiv preprint arXiv:2007.14672},
  year   = {2022}
}

Comments

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

R2 v1 2026-06-23T17:29:13.082Z