A statistical analysis for deepfake videos forgery traces recognition followed by a fine-tuned InceptionResNetV2 detection technique

IF 1.5 4区 医学 Q2 MEDICINE, LEGAL Journal of forensic sciences Pub Date : 2024-11-19 DOI:10.1111/1556-4029.15665
Sandhya MSc, Abhishek Kashyap PhD
{"title":"A statistical analysis for deepfake videos forgery traces recognition followed by a fine-tuned InceptionResNetV2 detection technique","authors":"Sandhya MSc,&nbsp;Abhishek Kashyap PhD","doi":"10.1111/1556-4029.15665","DOIUrl":null,"url":null,"abstract":"<p>Deepfake videos are growing progressively more competent because of the rapid advancements in artificial intelligence and deep learning technology. This has led to substantial problems around propaganda, privacy, and security. This research provides an analytically novel method for detecting deepfake videos using temporal discrepancies of the various statistical features of video at the pixel level, followed by a deep learning algorithm. To detect minute aberrations typical of deepfake manipulations, this study focuses on both spatial information inside individual frames and temporal correlations between subsequent frames. This study primarily provides a novel Euclidean distance variation probability score value for directly commenting on the authenticity of a deepfake video. Next, fine-tuning of InceptionResNetV2 with the addition of a dense layer is trained FaceForensics++ for deepfake detection. The proposed fine-tuned model outperforms the existing techniques as its testing accuracy on unseen data outperforms the existing methods. The propsd method achieved an accuracy of 99.80% for FF++ dataset and 97.60% accuracy for CelebDF dataset.</p>","PeriodicalId":15743,"journal":{"name":"Journal of forensic sciences","volume":"70 1","pages":"349-368"},"PeriodicalIF":1.5000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of forensic sciences","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/1556-4029.15665","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICINE, LEGAL","Score":null,"Total":0}
引用次数: 0

Abstract

Deepfake videos are growing progressively more competent because of the rapid advancements in artificial intelligence and deep learning technology. This has led to substantial problems around propaganda, privacy, and security. This research provides an analytically novel method for detecting deepfake videos using temporal discrepancies of the various statistical features of video at the pixel level, followed by a deep learning algorithm. To detect minute aberrations typical of deepfake manipulations, this study focuses on both spatial information inside individual frames and temporal correlations between subsequent frames. This study primarily provides a novel Euclidean distance variation probability score value for directly commenting on the authenticity of a deepfake video. Next, fine-tuning of InceptionResNetV2 with the addition of a dense layer is trained FaceForensics++ for deepfake detection. The proposed fine-tuned model outperforms the existing techniques as its testing accuracy on unseen data outperforms the existing methods. The propsd method achieved an accuracy of 99.80% for FF++ dataset and 97.60% accuracy for CelebDF dataset.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
对深度伪造视频的伪造痕迹识别进行统计分析,然后采用经过微调的 InceptionResNetV2 检测技术。
由于人工智能和深度学习技术的飞速发展,深度伪造视频的能力日益增强。这导致了围绕宣传、隐私和安全的大量问题。本研究提供了一种新颖的分析方法,利用像素级视频各种统计特征的时间差异,再利用深度学习算法来检测深度伪造视频。为了检测典型的深度伪造操作的微小畸变,本研究重点关注单个帧内的空间信息和后续帧之间的时间相关性。本研究主要提供了一种新颖的欧氏距离变化概率分值,用于直接评判深度伪造视频的真伪。接下来,通过增加密集层对 InceptionResNetV2 进行微调,训练 FaceForensics++ 进行深度伪造检测。所提出的微调模型优于现有技术,因为它在未见数据上的测试准确率优于现有方法。propsd 方法在 FF++ 数据集上的准确率达到 99.80%,在 CelebDF 数据集上的准确率达到 97.60%。
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 去求助
来源期刊
Journal of forensic sciences
Journal of forensic sciences 医学-医学:法
CiteScore
4.00
自引率
12.50%
发文量
215
审稿时长
2 months
期刊介绍: The Journal of Forensic Sciences (JFS) is the official publication of the American Academy of Forensic Sciences (AAFS). It is devoted to the publication of original investigations, observations, scholarly inquiries and reviews in various branches of the forensic sciences. These include anthropology, criminalistics, digital and multimedia sciences, engineering and applied sciences, pathology/biology, psychiatry and behavioral science, jurisprudence, odontology, questioned documents, and toxicology. Similar submissions dealing with forensic aspects of other sciences and the social sciences are also accepted, as are submissions dealing with scientifically sound emerging science disciplines. The content and/or views expressed in the JFS are not necessarily those of the AAFS, the JFS Editorial Board, the organizations with which authors are affiliated, or the publisher of JFS. All manuscript submissions are double-blind peer-reviewed.
期刊最新文献
Issue Information Facing the future: Technology and “advocacy” at the American Academy of Forensic Sciences How specific is the specificity rule in duty to warn or protect jurisprudence following the Pennsylvania Supreme Court's Maas decision? Retraction: M. Ashton, N. Czado, M. Harrel, S. Hughes. “Genotyping strategies for tissues fixed with various embalming fluids for human identification, databasing, and traceability,” Journal of Forensic Sciences (Early View) https://doi.org/10.1111/1556-4029.15414. Survey on forensic DNA biology training in forensic science service laboratories in the United States
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1