Deepfake Detection on Videos Based on Ratio Images

R. L. Testa, Ariane Machado-Lima, Fátima L. S. Nunes
{"title":"Deepfake Detection on Videos Based on Ratio Images","authors":"R. L. Testa, Ariane Machado-Lima, Fátima L. S. Nunes","doi":"10.1109/IIAIAAI55812.2022.00086","DOIUrl":null,"url":null,"abstract":"Deepfake detection comes as a countermeasure to identify fake media content to reduce its harmful implications. Most detection approaches rely on identifying specific artifacts that can quickly become obsolete due to the fast advance in facial forgery methods. Some facial manipulation detection methods use temporal information to classify the video as real or fake. These methods mainly rely on 3D CNN architectures or two-stream networks using frame and video features. Our method not only considers temporal aspects, but it comes from a different perspective: extracting features that can account for inter-frame changes on a video. Inspired by the concept of ratio images, we extract features based on the ratio between adjacent frames for the face and its background. The experimental evaluation showed better results in intra- and cross-dataset tests on FaceForensics++ (FF++) and CelebDF datasets compared to the state-of-the-art deepfake detection approaches in the assessment with seen and unseen facial manipulation methods, as well as in seen and unseen video settings. In the intra-dataset experiment, the model resulted in an AUC of 100% for both CelebDF and FF++ datasets. In the cross dataset experiment, the model resulted in an AUC of 98% when trained with CelebDF and tested with FF++ and 86% when trained with FF++ and tested with CelebDF.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IIAIAAI55812.2022.00086","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Deepfake detection comes as a countermeasure to identify fake media content to reduce its harmful implications. Most detection approaches rely on identifying specific artifacts that can quickly become obsolete due to the fast advance in facial forgery methods. Some facial manipulation detection methods use temporal information to classify the video as real or fake. These methods mainly rely on 3D CNN architectures or two-stream networks using frame and video features. Our method not only considers temporal aspects, but it comes from a different perspective: extracting features that can account for inter-frame changes on a video. Inspired by the concept of ratio images, we extract features based on the ratio between adjacent frames for the face and its background. The experimental evaluation showed better results in intra- and cross-dataset tests on FaceForensics++ (FF++) and CelebDF datasets compared to the state-of-the-art deepfake detection approaches in the assessment with seen and unseen facial manipulation methods, as well as in seen and unseen video settings. In the intra-dataset experiment, the model resulted in an AUC of 100% for both CelebDF and FF++ datasets. In the cross dataset experiment, the model resulted in an AUC of 98% when trained with CelebDF and tested with FF++ and 86% when trained with FF++ and tested with CelebDF.
基于比例图像的视频深度假检测
深度造假检测是一种识别虚假媒体内容以减少其有害影响的对策。大多数检测方法依赖于识别特定的工件,由于面部伪造方法的快速发展,这些工件可能很快就会过时。一些面部操作检测方法利用时间信息对视频进行真假分类。这些方法主要依赖于3D CNN架构或使用帧和视频特征的双流网络。我们的方法不仅考虑了时间方面,而且从不同的角度来考虑:提取可以解释视频帧间变化的特征。受比例图像概念的启发,我们根据人脸与其背景的相邻帧之间的比例提取特征。实验评估显示,与最先进的深度伪造检测方法相比,在face取证++ (FF++)和CelebDF数据集上的内部和跨数据集测试结果更好,包括可见和不可见的面部操作方法,以及可见和不可见的视频设置。在数据集内实验中,该模型对CelebDF和FF++数据集的AUC均为100%。在交叉数据集实验中,当使用CelebDF训练并使用FF++测试时,该模型的AUC为98%,而使用FF++训练并使用CelebDF测试时,该模型的AUC为86%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信