Adversarial Medical Image With Hierarchical Feature Hiding

doi:10.1109/TMI.2023.3335098

	Adversarial Medical Image With Hierarchical Feature Hiding
	Yao, Qingsong 1,2; He, Zecheng 3; Li, Yuexiang 4,5; Lin, Yi 6; Ma, Kai 4; Zheng, Yefeng 4; Zhou, S. Kevin 7,8,9
	2024-04-01
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING
ISSN	0278-0062
卷号	43 期号:4 页码:1296-1307
摘要	Deep learning based methods for medical images can be easily compromised by adversarial examples (AEs), posing a great security flaw in clinical decision-making. It has been discovered that conventional adversarial attacks like PGD which optimize the classification logits, are easy to distinguish in the feature space, resulting in accurate reactive defenses. To better understand this phenomenon and reassess the reliability of the reactive defenses for medical AEs, we thoroughly investigate the characteristic of conventional medical AEs. Specifically, we first theoretically prove that conventional adversarial attacks change the outputs by continuously optimizing vulnerable features in a fixed direction, thereby leading to outlier representations in the feature space. Then, a stress test is conducted to reveal the vulnerability of medical images, by comparing with natural images. Interestingly, this vulnerability is a double-edged sword, which can be exploited to hide AEs. We then propose a simple-yet-effective hierarchical feature constraint (HFC), a novel add-on to conventional white-box attacks, which assists to hide the adversarial feature in the target feature distribution. The proposed method is evaluated on three medical datasets, both 2D and 3D, with different modalities. The experimental results demonstrate the superiority of HFC, i.e., it bypasses an array of state-of-the-art adversarial medical AE detectors more efficiently than competing adaptive attacks, which reveals the deficiencies of medical reactive defense and allows to develop more robust defenses in future.
关键词	Security in machine learning adversarial attacks and defense
DOI	10.1109/TMI.2023.3335098
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001196733400025
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39887
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhou, S. Kevin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 10045, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Meta Real Labs, Burlingame, CA 94010 USA 4.Jarvis Res Ctr, Tencent YouTu Lab, Shenzhen 518057, Peoples R China 5.Guangxi Med Univ, Guangxi Key Lab Genom & Personalized Med, Med AI ReS MARS Grp, Nanning 530021, Peoples R China 6.Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Hong Kong, Peoples R China 7.Univ Sci & Technol China, Sch Biomed Engn, Hefei 230026, Peoples R China 8.Univ Sci & Technol China, Suzhou Inst Adv Res, Hefei 230026, Peoples R China 9.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China
推荐引用方式 GB/T 7714	Yao, Qingsong,He, Zecheng,Li, Yuexiang,et al. Adversarial Medical Image With Hierarchical Feature Hiding[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2024,43(4):1296-1307.
APA	Yao, Qingsong.,He, Zecheng.,Li, Yuexiang.,Lin, Yi.,Ma, Kai.,...&Zhou, S. Kevin.(2024).Adversarial Medical Image With Hierarchical Feature Hiding.IEEE TRANSACTIONS ON MEDICAL IMAGING,43(4),1296-1307.
MLA	Yao, Qingsong,et al."Adversarial Medical Image With Hierarchical Feature Hiding".IEEE TRANSACTIONS ON MEDICAL IMAGING 43.4(2024):1296-1307.