F-mixup: Attack CNNs from Fourier perspective | |
Xiu-Chuan Li; Xu-Yao Zhang; Fei Yin; Cheng-Lin Liu | |
2021 | |
会议日期 | January 10-15, 2021 |
会议地点 | Milan, Italy |
英文摘要 | Recent research has revealed that deep neural networks are highly vulnerable to adversarial examples. In this paper, different from most adversarial attacks which directly modify pixels in spatial domain, we propose a novel black-box attack in frequency domain, named as f-mixup, based on the property of natural images and perception disparity between human-visual system (HVS) and convolutional neural networks (CNNs): First, natural images tend to have the bulk of their Fourier spectrums concentrated on the low frequency domain; Second, HVS is much less sensitive to high frequencies while CNNs can utilize both low and high frequency information to make predictions. Extensive experiments are conducted and show that deeper CNNs tend to concentrate more on the higher frequency domain, which may explain the contradiction between robustness and accuracy. In addition, we compared f-mixup with existing attack methods and observed that our approach possesses great advantages. Finally, we show that f-mixup can be also incorporated in training to make deep CNNs defensible against a kind of perturbations effectively. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/47477] |
专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
通讯作者 | Xu-Yao Zhang |
作者单位 | 中科院自动化所 |
推荐引用方式 GB/T 7714 | Xiu-Chuan Li,Xu-Yao Zhang,Fei Yin,et al. F-mixup: Attack CNNs from Fourier perspective[C]. 见:. Milan, Italy. January 10-15, 2021. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论