Deep learning-based video forgery detection

The harm of deepfake is becoming more and more serious in today’s new media era, especially in video deepfake. Therefore, we conduct experiments on two public video datasets Celeb-DF-v2, DFDC and a relabelled TMC media dataset, using an end-to-end structure of video input and video classification ou...

Full description

Saved in:
Bibliographic Details
Main Author: Cao, Xinyi
Other Authors: Alex Chichung Kot
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/157582
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-157582
record_format dspace
spelling sg-ntu-dr.10356-1575822022-05-12T11:49:30Z Deep learning-based video forgery detection Cao, Xinyi Alex Chichung Kot School of Electrical and Electronic Engineering EACKOT@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering::Electronic systems::Signal processing The harm of deepfake is becoming more and more serious in today’s new media era, especially in video deepfake. Therefore, we conduct experiments on two public video datasets Celeb-DF-v2, DFDC and a relabelled TMC media dataset, using an end-to-end structure of video input and video classification output, combining the state-of-the-art Convolutional Neural Network (CNN) models with the Vision Transformer architecture and the Long Short-Term Memory (LSTM) architecture. It is found that the longer the frame length of the video, the more accurate the detection. In the case of video length of 30 frames, we obtain competitive AUC scores of 0.932 on the DFDC dataset, 0.980 on the Celeb-DF-V2 dataset and 0.953 on the TMC dataset. Master of Science (Signal Processing) 2022-05-12T11:49:30Z 2022-05-12T11:49:30Z 2022 Thesis-Master by Coursework Cao, X. (2022). Deep learning-based video forgery detection. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157582 https://hdl.handle.net/10356/157582 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Cao, Xinyi
Deep learning-based video forgery detection
description The harm of deepfake is becoming more and more serious in today’s new media era, especially in video deepfake. Therefore, we conduct experiments on two public video datasets Celeb-DF-v2, DFDC and a relabelled TMC media dataset, using an end-to-end structure of video input and video classification output, combining the state-of-the-art Convolutional Neural Network (CNN) models with the Vision Transformer architecture and the Long Short-Term Memory (LSTM) architecture. It is found that the longer the frame length of the video, the more accurate the detection. In the case of video length of 30 frames, we obtain competitive AUC scores of 0.932 on the DFDC dataset, 0.980 on the Celeb-DF-V2 dataset and 0.953 on the TMC dataset.
author2 Alex Chichung Kot
author_facet Alex Chichung Kot
Cao, Xinyi
format Thesis-Master by Coursework
author Cao, Xinyi
author_sort Cao, Xinyi
title Deep learning-based video forgery detection
title_short Deep learning-based video forgery detection
title_full Deep learning-based video forgery detection
title_fullStr Deep learning-based video forgery detection
title_full_unstemmed Deep learning-based video forgery detection
title_sort deep learning-based video forgery detection
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/157582
_version_ 1734310307953639424