Can I read Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging on EtoBox?

Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging by Jia, Xiaojun; Chen, Yuefeng; Mao, Xiaofeng; Duan, Ranjie; Gu, Jindong; Zhang, Rong; Xue, Hui; Cao, Xiaochun is a scholarly article available to read on EtoBox.

What is Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging about?

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results in poor robustness performance. Catastrophic Overfitting describes the phenomenon of a sudden and significant decrease in robust accuracy during the training of fast adversarial training. Many effective techniques have been developed to prevent Catastrophic Overfitting and improve the model robustness from different perspectives. However, these techniques adopt inconsistent training settings and require different training costs, i.e, training time and memory costs, leading to unfair comparisons. In this paper, we conduct a comprehensive study of over 10 fast adversarial training methods in terms of adversarial robustness and training costs. We revisit the effectiveness and efficiency of fast adversarial training techniques in preventing Catastrophic Overfitting from the perspective of model local nonlinearity and propose an effective Lipschitz regularization method for fast adversarial training. Furthermore, we explore the effect of data augmentat

Author

Jia, Xiaojun; Chen, Yuefeng; Mao, Xiaofeng; Duan, Ranjie; Gu, Jindong; Zhang, Rong; Xue, Hui; Cao, Xiaochun

Published

2023

Language

EN