中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Temporal sparse adversarial attack on sequence-based gait recognition

文献类型:期刊论文

作者He, Ziwen1,3; Wang, Wei2,3; Dong, Jing3; Tan, Tieniu3
刊名PATTERN RECOGNITION
出版日期2023
卷号133页码:11
ISSN号0031-3203
关键词Adversarial attack Gait recognition Temporal sparsity
DOI10.1016/j.patcog.2022.109028
通讯作者Wang, Wei(wwang@nlpr.ia.ac.cn)
英文摘要Gait recognition is widely used in social security applications due to its advantages in long-distance hu-man identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information. However, their robustness under adversarial attacks in an open world has not been clearly explored. In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. To this end, we propose a novel temporal sparse adversarial attack method. Different from previous additive noise models which add perturbations on original samples, we employ a generative adversarial network based architecture to semantically generate adversarial high -quality gait silhouettes or video frames. Moreover, by sparsely substituting or inserting a few adversarial gait silhouettes, the proposed method ensures its imperceptibility and achieves a strong attack ability. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.(c) 2022 Elsevier Ltd. All rights reserved.
资助项目National Key Research and Development Pro-gram of China ; National Natural Science Foundation of China ; [2021YFC3320103] ; [61972395]
WOS研究方向Computer Science ; Engineering
语种英语
出版者ELSEVIER SCI LTD
WOS记录号WOS:000870987900007
资助机构National Key Research and Development Pro-gram of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/50508]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Wang, Wei
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
He, Ziwen,Wang, Wei,Dong, Jing,et al. Temporal sparse adversarial attack on sequence-based gait recognition[J]. PATTERN RECOGNITION,2023,133:11.
APA He, Ziwen,Wang, Wei,Dong, Jing,&Tan, Tieniu.(2023).Temporal sparse adversarial attack on sequence-based gait recognition.PATTERN RECOGNITION,133,11.
MLA He, Ziwen,et al."Temporal sparse adversarial attack on sequence-based gait recognition".PATTERN RECOGNITION 133(2023):11.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

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。