BZNet: Unsupervised Multi-scale Branch Zooming Network for Detecting Low-quality Deepfake Videos
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, S.[Lee, S.] | - |
dc.contributor.author | An, J.[An, J.] | - |
dc.contributor.author | Woo, S.S.[Woo, S.S.] | - |
dc.date.accessioned | 2022-09-13T04:45:02Z | - |
dc.date.available | 2022-09-13T04:45:02Z | - |
dc.date.created | 2022-09-13 | - |
dc.date.issued | 2022-04-25 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/98869 | - |
dc.description.abstract | Generating a deep learning-based fake video has become no longer rocket science. The advancement of automated Deepfake (DF) generation tools that mimic certain targets has rendered society vulnerable to fake news or misinformation propagation. In real-world scenarios, DF videos are compressed to low-quality (LQ) videos, taking up less storage space and facilitating dissemination through the web and social media. Such LQ DF videos are much more challenging to detect than high-quality (HQ) DF videos. To address this challenge, we rethink the design of standard deep learning-based DF detectors, specifically exploiting feature extraction to enhance the features of LQ images. We propose a novel LQ DF detection architecture, multi-scale Branch Zooming Network (BZNet), which adopts an unsupervised super-resolution (SR) technique and utilizes multi-scale images for training. We train our BZNet only using highly compressed LQ images and experiment under a realistic setting, where HQ training data are not readily accessible. Extensive experiments on the FaceForensics++ LQ and GAN-generated datasets demonstrate that our BZNet architecture improves the detection accuracy of existing CNN-based classifiers by 4.21% on average. Furthermore, we evaluate our method against a real-world Deepfake-in-the-Wild dataset collected from the internet, which contains 200 videos featuring 50 celebrities worldwide, outperforming the state-of-the-art methods by 4.13%. © 2022 ACM. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Association for Computing Machinery, Inc | - |
dc.title | BZNet: Unsupervised Multi-scale Branch Zooming Network for Detecting Low-quality Deepfake Videos | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, S.[Lee, S.] | - |
dc.contributor.affiliatedAuthor | An, J.[An, J.] | - |
dc.contributor.affiliatedAuthor | Woo, S.S.[Woo, S.S.] | - |
dc.identifier.doi | 10.1145/3485447.3512245 | - |
dc.identifier.scopusid | 2-s2.0-85129840022 | - |
dc.identifier.wosid | 000852713003058 | - |
dc.identifier.bibliographicCitation | WWW 2022 - Proceedings of the ACM Web Conference 2022, pp.3500 - 3510 | - |
dc.relation.isPartOf | WWW 2022 - Proceedings of the ACM Web Conference 2022 | - |
dc.citation.title | WWW 2022 - Proceedings of the ACM Web Conference 2022 | - |
dc.citation.startPage | 3500 | - |
dc.citation.endPage | 3510 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Cybernetics | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.subject.keywordAuthor | Deepfake Detection | - |
dc.subject.keywordAuthor | Forensics | - |
dc.subject.keywordAuthor | Low-quality Deepfakes | - |
dc.subject.keywordAuthor | Multi-scale Learning | - |
dc.subject.keywordAuthor | Unsupervised Super-Resolution | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(03063) 25-2, SUNGKYUNKWAN-RO, JONGNO-GU, SEOUL, KOREAsamsunglib@skku.edu
COPYRIGHT © 2021 SUNGKYUNKWAN UNIVERSITY ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.