FrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeong, Y. | - |
dc.contributor.author | Kim, D. | - |
dc.contributor.author | Ro, Y. | - |
dc.contributor.author | Choi, Jong Won | - |
dc.date.accessioned | 2024-01-08T21:31:13Z | - |
dc.date.available | 2024-01-08T21:31:13Z | - |
dc.date.issued | 2022-02 | - |
dc.identifier.issn | 2159-5399 | - |
dc.identifier.issn | 2374-3468 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69562 | - |
dc.description.abstract | Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own analysis and the previous studies to originate from the frequency-level artifacts in generated images. We find that ignoring the frequency-level artifacts can improve the detector's generalization across various GAN models, but it can reduce the model's performance for the trained GAN models. Thus, we design a framework to generalize the deepfake detector for both the known and unseen GAN models. Our framework generates the frequency-level perturbation maps to make the generated images indistinguishable from the real images. By updating the deepfake detector along with the training of the perturbation generator, our model is trained to detect the frequency-level artifacts at the initial iterations and consider the image-level irregularities at the last iterations. For experiments, we design new test scenarios varying from the training settings in GAN models, color manipulations, and object categories. Numerous experiments validate the state-of-the-art performance of our deepfake detector. Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. | - |
dc.format.extent | 9 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Association for the Advancement of Artificial Intelligence | - |
dc.title | FrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations | - |
dc.type | Article | - |
dc.identifier.bibliographicCitation | Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022, v.36, pp 888 - 896 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 000893636201015 | - |
dc.identifier.scopusid | 2-s2.0-85147665748 | - |
dc.citation.endPage | 896 | - |
dc.citation.startPage | 888 | - |
dc.citation.title | Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022 | - |
dc.citation.volume | 36 | - |
dc.identifier.url | https://arxiv.org/abs/2202.03347 | - |
dc.type.docType | Conference Paper | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang 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.