UM  > 科技學院  > 電腦及資訊科學系
SIFT Keypoint Removal and Injection via Convex Relaxation
Yuanman Li1; Jiantao Zhou1; An Cheng2; Xianming Liu3; Yuan Yan Tang1
2016-08-01
Source PublicationIEEE Transactions on Information Forensics and Security
ISSN1556-6013
Volume11Issue:8Pages:1722-1735
Abstract

Scale invariant feature transform (SIFT), as one of the most popular local feature extraction algorithms, has been widely employed in many computer vision and multimedia security applications. Although SIFT has been extensively investigated from various perspectives, its security against malicious attacks has rarely been discussed. In this paper, we show that the SIFT keypoints can be effectively removed with minimized distortion on the processed image. The SIFT keypoint removal is formulated as a constrained optimization problem, where the constraints are carefully designed to suppress the existence of local extrema and prevent generating new keypoints within a local cuboid in the scale space. To hide the traces of performing SIFT keypoint removal, we then propose to inject a large number of fake SIFT keypoints into the previously cleaned image with minimized distortion. As demonstrated experimentally, our proposed SIFT removal and injection algorithms significantly outperform the state-of-the-art techniques. Furthermore, it is shown that the combined SIFT keypoint removal and injection attack strategy is capable of defeating the most powerful forensic detector designed for SIFT keypoint removal. Our results suggest that an authorization mechanism is required for SIFT-based systems to verify the validity of the input data, so as to achieve high reliability.

KeywordConvex Optimization Keypoint Injection Keypoint Removal Sift
DOIhttps://doi.org/10.1109/TIFS.2016.2553645
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000377114600008
Fulltext Access
Citation statistics
Cited Times [WOS]:7   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorYuanman Li; Jiantao Zhou; An Cheng; Xianming Liu; Yuan Yan Tang
Affiliation1.Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau 999078, China
2.Meitu, Inc., Xiamen 361008, China
3.School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
First Author AffilicationFaculty of Science and Technology
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Yuanman Li,Jiantao Zhou,An Cheng,et al. SIFT Keypoint Removal and Injection via Convex Relaxation[J]. IEEE Transactions on Information Forensics and Security,2016,11(8):1722-1735.
APA Yuanman Li,Jiantao Zhou,An Cheng,Xianming Liu,&Yuan Yan Tang.(2016).SIFT Keypoint Removal and Injection via Convex Relaxation.IEEE Transactions on Information Forensics and Security,11(8),1722-1735.
MLA Yuanman Li,et al."SIFT Keypoint Removal and Injection via Convex Relaxation".IEEE Transactions on Information Forensics and Security 11.8(2016):1722-1735.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yuanman Li]'s Articles
[Jiantao Zhou]'s Articles
[An Cheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yuanman Li]'s Articles
[Jiantao Zhou]'s Articles
[An Cheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yuanman Li]'s Articles
[Jiantao Zhou]'s Articles
[An Cheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.