Forensics and Analysis of Deepfake Videos
Криминалистика и анализ видео «deepfake»
2020-04-01
SCID: 54.1/unv633qr
Discuss with AI
DFT-MFDeepfake detectiondeep learninglip/mouth movement analysismouth features
Figures from the paper
Abstract (AI)
The spread of smartphones with high quality digital cameras in combination with easy access to a myriad of software apps for recording, editing and sharing videos and digital images in combination with deep learning AI platforms has spawned a new phenomenon of faking videos known as Deepfake. We design and implement a deep-fake detection model with mouth features (DFT-MF), using deep learning approach to detect Deepfake videos by isolating, analyzing and verifying lip/mouth movement. Experiments conducted against datasets that contain both fake and real videos showed favorable classification performance for DFT-MF model especially when compared with other work in this area.
Key Findings
1
DFT-MF outperforms or compares favorably with other existing works in deepfake detection focused on video datasets.
2
DFT-MF uses a deep learning approach to detect deepfake videos by verifying mouth and lip movement features.
3
Experiments on datasets containing both fake and real videos show favorable classification performance for DFT-MF.
4
The paper introduces DFT-MF, a deepfake detection model that focuses on isolating and analyzing lip/mouth movements.
Research Object
Deepfake videos
Research Subject
Detection and forensic analysis of lip/mouth movement features for classifying videos as real or deepfake using a DFT-MF deep learning model
Publication Details
Publication Date
2020-04-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest