Adaptive Adversarial Norm Space for Efficient Adversarial Training
Hui Kuurila-Zhang (University of Oulu),* Haoyu Chen (University of Oulu), Guoying Zhao (University of Oulu)
The 34th British Machine Vision Conference
Abstract
Adversarial training draws increasing attention as it can improve the robustness of deep neural networks against adversarial examples. Recent research proposed to adaptively adjust the adversarial strategy for a better learning process. However, those approaches rely on cumbersome computations for getting the optimal adversarial strategy. This paper offers a novel perspective on adversarial strategies by examining the adversarial examples' norm space. We show that cyclically altering the adversarial norm space can significantly enhance the network's robustness. Based on the observations, we propose a simple yet effective Entropy-Guided Cyclical Adversarial Strategy (ECAS) to explicitly adjust the norm space of the adversarial examples, forming an elastic-perturbation mechanism in the adversarial training framework that adaptively perturbs models based on entropy. Extensive experiments demonstrate that our proposed method can achieve promising performances and substantially reduce computational time compared to state-of-the-art methods. Moreover, we also show that ECAS can be directly plugged into existing adversarial training methods to further boost performances. The implementation of ECAS is at https://github.com/huizhg/ECAS.Video
Citation
@inproceedings{Kuurila-Zhang_2023_BMVC,
author = {Hui Kuurila-Zhang and Haoyu Chen and Guoying Zhao},
title = {Adaptive Adversarial Norm Space for Efficient Adversarial Training},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0781.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by