Adversarial Analysis for Source Camera Identification

doi:10.1109/TCSVT.2020.3047084

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Adversarial Analysis for Source Camera Identification
	Wang, Bo 3; Zhao, Mengnan 3; Wang, Wei 1; Dai, Xiaorui 3; Li, Yi 2; Guo, Yanqing 3
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2021-11-01
卷号	31 期号:11 页码:4174-4186
关键词	Cameras Feature extraction Forensics Task analysis Perturbation methods Neural networks Training Adversarial attacks fingerprint copy-move attack joint feature-based auto-learning attack relation mismatch
ISSN号	1051-8215
DOI	10.1109/TCSVT.2020.3047084
通讯作者	Wang, Wei(wei.wong@ia.ac.cn)
英文摘要	Recent studies highlight the vulnerability of convolutional neural networks (CNNs) to adversarial attacks, which also calls into question the reliability of forensic methods. Existing adversarial attacks generate one-to-one noise, which means these methods have not learned the fingerprint information. Therefore, we introduce two powerful attacks, fingerprint copy-move attack, and joint feature-based auto-learning attack. To validate the performance of attack methods, we move a step ahead and introduce the higher possible defense mechanism relation mismatch. which expands the characterization differences of classifiers in the same classification network. Extensive experiments show that relation mismatch is superior in recognizing adversarial examples and prove that the proposed fingerprint-based attacks are more powerful. Both proposed attacks show excellent attack transferability to unknown samples. The Pytorch (R) implementations of these methods can download from an open-source GitHub project https://github.com/Dlut-lab-zmn/Source-attack.
资助项目	National Natural Science Foundation of China[U1936117] ; National Natural Science Foundation of China[U1736119] ; National Natural Science Foundation of China[61972395] ; National Natural Science Foundation of China[61772111] ; Beijing Natural Science Foundation[4192058]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000711805800006
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/46356]
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.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Beijing 100190, Peoples R China 2.Dalian Univ Technol, Sch Artificial Intelligence, Dalian 116024, Peoples R China 3.Dalian Univ Technol, Sch Informat & Commun Engn, Dalian 116024, Peoples R China
推荐引用方式 GB/T 7714	Wang, Bo,Zhao, Mengnan,Wang, Wei,et al. Adversarial Analysis for Source Camera Identification[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,31(11):4174-4186.
APA	Wang, Bo,Zhao, Mengnan,Wang, Wei,Dai, Xiaorui,Li, Yi,&Guo, Yanqing.(2021).Adversarial Analysis for Source Camera Identification.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,31(11),4174-4186.
MLA	Wang, Bo,et al."Adversarial Analysis for Source Camera Identification".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 31.11(2021):4174-4186.