APSIPA Transactions on Signal and Information Processing > Vol 11 > Issue 2

Detecting Deepfake Videos in Data Scarcity Conditions by Means of Video Coding Features

Jun Wang, Department of Information Engineering and Mathematics, University of Siena, Italy, j.wang@student.unisi.it , Omran Alamayreh, Department of Information Engineering and Mathematics, University of Siena, Italy, Benedetta Tondi, Department of Information Engineering and Mathematics, University of Siena, Italy, Andrea Costanzo, Department of Information Engineering and Mathematics, University of Siena, Italy, Mauro Barni, Department of Information Engineering and Mathematics, University of Siena, Italy
 
Suggested Citation
Jun Wang, Omran Alamayreh, Benedetta Tondi, Andrea Costanzo and Mauro Barni (2022), "Detecting Deepfake Videos in Data Scarcity Conditions by Means of Video Coding Features", APSIPA Transactions on Signal and Information Processing: Vol. 11: No. 2, e43. http://dx.doi.org/10.1561/116.00000032

Publication Date: 28 Dec 2022
© 2022 J. Wang, O. Alamayreh, B. Tondi, A. Costanzo and M. Barni
 
Subjects
 
Keywords
Deepfake detectionvideo forensicsdeep learning for forensicsvideo coding
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 744 times

In this article:
Introduction 
Related Work 
DeepFake Detection based on Video Coding Features 
Methodology 
Experimental Results 
Conclusions 
References 

Abstract

The most powerful deepfake detection methods developed so far are based on deep learning, requiring that large amounts of training data representative of the specific task are available to the trainer. In this paper, we propose a feature-based method for video deepfake detection that can work in data scarcity conditions, that is, when only very few examples are available to the forensic analyst. The proposed method is based on video coding analysis and relies on a simple footprint obtained from the motion prediction modes in the video sequence. The footprint is extracted from video sequences and used to train a simple linear Support Vector Machine classifier. The effectiveness of the proposed method is validated experimentally on three different datasets, namely, a synthetic street video dataset and two datasets of Deepfake face videos.

DOI:10.1561/116.00000032

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Multi-Disciplinary Dis/Misinformation Analysis and Countermeasures: Articles Overview
See the other articles that are part of this special issue.