Enhancing fast adversarial training with momentum

Fast adversarial training (FAT) has emerged as an effective strategy to enhance the robustness of deep learning models against adversarial attacks. However, catastrophic overfitting remains a significant challenge, where models experience a sudden deterioration in their adversarial robustness. To address this issue, we propose a novel approach combining momentum-driven initialization and max ...

To address this issue, we propose a novel approach combining momentum-driven initialization and max-norm regularization, termed MIMR. Our momentum-driven initialization method maintains high-quality adversarial examples throughout training by leveraging previous perturbations, without increasing computational costs.
Enhancing Fast Adversarial Training with Momentum

In Fast Adversarial Training (FAT) improve the adversarial example quality with (a) Momentum-driven initialization and (b) Max-norm regularization to enhance robustness. In this work, we conduct an extensive evaluation of the Momentum -Initialized Max-Norm Regularization (MIMR) method in terms of adversarial robustness and computational efficiency.
Our momentum-driven initialization method maintains high-quality adversarial examples throughout training by leveraging previous perturbations, without increasing computational costs.

Enhancing fast adversarial training with momentum
A novel approach combining momentum-driven initialization and max-norm regularization, termed MIMR, which not only mitigates catastrophic overfitting but also achieves higher classification accuracy under various attacks, such as PGD, C&W, and AutoAttack. Fast adversarial training (FAT) has emerged as an effective strategy to enhance the robustness of deep learning models against adversarial ...
Enhancing fast adversarial training with momentum-driven initialization and max-norm regularization for robust deep learning models. The Visual Computer, 41 (13):11389-11406, October 2025. [doi]

Enhancing fast adversarial training with momentum
Enhancing fast adversarial training with momentum-driven initialization ... ... Trending. More
Fast Adversarial Training (FAT) enhances model robustness against adversarial attacks with minimal computational overhead. However, standard FAT often leads to catastrophic overfitting and low robustness due to the weak perturbation initialization . To address this, we propose a refined FAT framework, Precision-Aware Adversarial Initialization (PAAI), that stabilizes FAT by generating ...

Enhancing fast adversarial training
Abstract Fast Adversarial Training (FAT) enhances model robustness against adversarial attacks with minimal computational overhead. However, standard FAT often leads to catastrophic overfitting and low robustness due to the weak perturbation initialization .







Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training . However, most AT methods are in face of expensive time and computational cost for calculating gradients at multiple steps in generating adversarial examples. To boost training efficiency, fast gradient sign method (FGSM) is adopted in fast AT methods by ...