[논문]Fighting Deepfake by Exposing the Convolutional Traces on Images

Guarnera, Luca; Giudice, Oliver; Battiato, Sebastiano

doi:10.1109/access.2020.3023037

Fighting Deepfake by Exposing the Convolutional Traces on Images 원문보기

IEEE access : practical research, open solutions, v.8, 2020년, pp.165085 - 165098

Guarnera, Luca (University of Catania, Catania, Italy) , Giudice, Oliver (University of Catania, Catania, Italy) , Battiato, Sebastiano (University of Catania, Catania, Italy)

Abstract ▼ AI-Helper

Advances in Artificial Intelligence and Image Processing are changing the way people interacts with digital images and video. Widespread mobile apps like FACEAPP make use of the most advanced Generative Adversarial Networks (GAN) to produce extreme transformations on human face photos such gender swap, aging, etc. The results are utterly realistic and extremely easy to be exploited even for non-experienced users. This kind of media object took the name of Deepfake and raised a new challenge in the multimedia forensics field: the Deepfake detection challenge. Indeed, discriminating a Deepfake from a real image could be a difficult task even for human eyes but recent works are trying to apply the same technology used for generating images for discriminating them with preliminary good results but with many limitations: employed Convolutional Neural Networks are not so robust, demonstrate to be specific to the context and tend to extract semantics from images. In this paper, a new approach aimed to extract a Deepfake fingerprint from images is proposed. The method is based on the Expectation-Maximization algorithm trained to detect and extract a fingerprint that represents the Convolutional Traces (CT) left by GANs during image generation. The CT demonstrates to have high discriminative power achieving better results than state-of-the-art in the Deepfake detection task also proving to be robust to different attacks. Achieving an overall classification accuracy of over 98%, considering Deepfakes from 10 different GAN architectures not only involved in images of faces, the CT demonstrates to be reliable and without any dependence on image semantic. Finally, tests carried out on Deepfakes generated by FACEAPP achieving 93% of accuracy in the fake detection task, demonstrated the effectiveness of the proposed technique on a real-case scenario.

참고문헌 (31)

10.1007/978-3-319-68548-9_57
J Mach Learn Res Visualizing data using t-SNE van der maaten 2008 9 2579

상세보기
10.1109/CVPR.2018.00916
He, Zhenliang, Zuo, Wangmeng, Kan, Meina, Shan, Shiguang, Chen, Xilin. AttGAN: Facial Attribute Editing by Only Changing What You Want. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, vol.28, no.11, 5464-5478.

상세보기
10.1109/CVPR.2019.01089
10.1109/CVPR.2019.00453
10.1109/CVPR42600.2020.00813
10.1145/2983468.2983470
10.1007/978-3-030-30645-8_65
10.1109/WIFS47025.2019.9035107
arXiv 1909 06122 FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces wang 2019
Proc IEEE/CVF Conf Comput Vis Pattern Recognit (CVPR) CNN-generated images are surprisingly easy to spot$\ldots$ for now wang 2020 1
arXiv 2004 12626 Preliminary forensics analysis of DeepFake images guarnera 2020
arXiv 1511 06434 Unsupervised representation learning with deep convolutional generative adversarial networks radford 2015
Proc Adv Neural Inf Process Syst Generative adversarial nets goodfellow 2014 2672
10.1109/CVPR.2019.00244
10.1109/ICCV.2017.244
10.1109/CVPRW50498.2020.00341
Moon, T.K.. The expectation-maximization algorithm. IEEE signal processing magazine, vol.13, no.6, 47-60.

상세보기
Iizuka, Satoshi, Simo-Serra, Edgar, Ishikawa, Hiroshi. Globally and locally consistent image completion. ACM transactions on graphics, vol.36, no.4, 1-14.

상세보기
10.1109/CVPR.2017.19
International Scholarly Research Notices An overview on image forensics piva 2013 2013
Verdoliva, Luisa. Media Forensics and DeepFakes: An Overview. IEEE journal of selected topics in signal processing, vol.14, no.5, 910-932.

상세보기
arXiv 1605 05396 Generative adversarial text to image synthesis reed 2016
arXiv 1710 10196 Progressive growing of GANs for improved quality, stability, and variation karras 2017
10.1109/ICCV.2019.00009
10.1109/CVPRW50498.2020.00344
Thies, Justus, Zollhöfer, Michael, Nießner, Matthias. Deferred neural rendering : image synthesis using neural textures. ACM transactions on graphics, vol.38, no.4, 1-12.

상세보기
10.1145/2929464.2929475
10.1109/ICCV.2019.00432
10.1109/CVPRW50498.2020.00329

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Fighting Deepfake by Exposing the Convolutional Traces on Images 원문보기

Abstract ▼ AI-Helper

참고문헌 (31)

이 논문을 인용한 문헌

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트