Bridged adversarial training

doi:10.1016/j.neunet.2023.08.024

Bridged adversarial training

2023-10-01

3

OA

AI

DOI：10.1016/j.neunet.2023.08.024

原文链接

查看原文

摘要

En 中文

Adversarial robustness is considered a required property of deep neural networks. In this study, we discover that adversarially trained models might have significantly different characteristics in terms of margin and smoothness, even though they show similar robustness. Inspired by the observation, we investigate the effect of different regularizers and discover the negative effect of the smoothness regularizer on maximizing the margin. Based on the analyses, we propose a new method called bridged adversarial training that mitigates the negative effect by bridging the gap between clean and adversarial examples. We provide theoretical and empirical evidence that the proposed method provides stable and better robustness, especially for large perturbations.& COPY; 2023 Elsevier Ltd. All rights reserved.

Keyword:

Neural networks

Adversarial robustness

Adversarial training

Adversarial defense

Bridged adversarial training

摘要

AI总结

期刊

机构