Saved in:
Bibliographic Details
Main Authors: Zhou, Dawei, Wang, Nannan, Gao, Xinbo, Han, Bo, Yu, Jun, Wang, Xiaoyu, Liu, Tongliang
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2106.05453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911810924314624
author Zhou, Dawei
Wang, Nannan
Gao, Xinbo
Han, Bo
Yu, Jun
Wang, Xiaoyu
Liu, Tongliang
author_facet Zhou, Dawei
Wang, Nannan
Gao, Xinbo
Han, Bo
Yu, Jun
Wang, Xiaoyu
Liu, Tongliang
contents Deep neural networks (DNNs) are vulnerable to adversarial noise. A range of adversarial defense techniques have been proposed to mitigate the interference of adversarial noise, among which the input pre-processing methods are scalable and show great potential to safeguard DNNs. However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting. A potential cause of this negative effect is that adversarial training examples are static and independent to the pre-processing model. To solve this problem, we investigate the influence of full adversarial examples which are crafted against the full model, and find they indeed have a positive impact on the robustness of defenses. Furthermore, we find that simply changing the adversarial training examples in pre-processing methods does not completely alleviate the robustness degradation effect. This is due to the adversarial risk of the pre-processed model being neglected, which is another cause of the robustness degradation effect. Motivated by above analyses, we propose a method called Joint Adversarial Training based Pre-processing (JATP) defense. Specifically, we formulate a feature similarity based adversarial risk for the pre-processing model by using full adversarial examples found in a feature space. Unlike standard adversarial training, we only update the pre-processing model, which prompts us to introduce a pixel-wise loss to improve its cross-model transferability. We then conduct a joint adversarial training on the pre-processing model to minimize this overall risk. Empirical results show that our method could effectively mitigate the robustness degradation effect across different target models in comparison to previous state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2106_05453
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Zhou, Dawei
Wang, Nannan
Gao, Xinbo
Han, Bo
Yu, Jun
Wang, Xiaoyu
Liu, Tongliang
Computer Vision and Pattern Recognition
Deep neural networks (DNNs) are vulnerable to adversarial noise. A range of adversarial defense techniques have been proposed to mitigate the interference of adversarial noise, among which the input pre-processing methods are scalable and show great potential to safeguard DNNs. However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting. A potential cause of this negative effect is that adversarial training examples are static and independent to the pre-processing model. To solve this problem, we investigate the influence of full adversarial examples which are crafted against the full model, and find they indeed have a positive impact on the robustness of defenses. Furthermore, we find that simply changing the adversarial training examples in pre-processing methods does not completely alleviate the robustness degradation effect. This is due to the adversarial risk of the pre-processed model being neglected, which is another cause of the robustness degradation effect. Motivated by above analyses, we propose a method called Joint Adversarial Training based Pre-processing (JATP) defense. Specifically, we formulate a feature similarity based adversarial risk for the pre-processing model by using full adversarial examples found in a feature space. Unlike standard adversarial training, we only update the pre-processing model, which prompts us to introduce a pixel-wise loss to improve its cross-model transferability. We then conduct a joint adversarial training on the pre-processing model to minimize this overall risk. Empirical results show that our method could effectively mitigate the robustness degradation effect across different target models in comparison to previous state-of-the-art approaches.
title Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2106.05453