Binary thresholding defense against adversarial attacks | |
Yutong Wang3,4; Wenwen Zhang2,4; Tianyu Shen3,4; Hui Yu1; Fei-Yue Wang4 | |
刊名 | Neurocomputing
![]() |
2021 | |
期号 | 445页码:61-71 |
关键词 | Binary thresholding Defense Adversarial training Adversarial attack |
英文摘要 | Convolutional neural networks are always vulnerable to adversarial attacks. In recent research, Projected Gradient Descent (PGD) has been recognized as the most effective attack method, and adversarial training on adversarial examples generated by PGD attack is the most reliable defense method. However, adversarial training requires a large amount of computation time. In this paper, we propose a fast, simple and strong defense method that achieves the best speed-accuracy trade-off. We first compare the feature maps of naturally trained model with adversarially trained model in same architecture, then we find the key of adversarially trained model lies on the binary thresholding the convolutional layers perform. Inspired by this, we perform binary thresholding to preprocess the input image and defend against PGD attack. On MNIST, our defense achieves 99.0% accuracy on clean images and 91.2% on white-box adversarial images. This performance is slightly better than adversarial training, and our method largely saves the computation time for retraining. On Fashion-MNIST and CIFAR-10, we train a new model on binarized images and use this model to defend against attack. Though its performance is not as good as adversarial training, it gains the best speed-accuracy trade-off. |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44700] ![]() |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Fei-Yue Wang |
作者单位 | 1.School of Creative Technologies, University of Portsmouth 2.School of Software Engineering, Xi'an Jiaotong University 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Yutong Wang,Wenwen Zhang,Tianyu Shen,et al. Binary thresholding defense against adversarial attacks[J]. Neurocomputing,2021(445):61-71. |
APA | Yutong Wang,Wenwen Zhang,Tianyu Shen,Hui Yu,&Fei-Yue Wang.(2021).Binary thresholding defense against adversarial attacks.Neurocomputing(445),61-71. |
MLA | Yutong Wang,et al."Binary thresholding defense against adversarial attacks".Neurocomputing .445(2021):61-71. |
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