Forged Video Detection Using Deep Learning: A SLR

In today’s digital landscape, video and image data have emerged as pivotal and widely adopted means of communication. They serve not only as a ubiquitous mode of conveying information but also as indispensable evidential and substantiating elements across diverse domains, encompassing law enforcemen...

Full description

Saved in:
Bibliographic Details
Main Authors: Maryam Munawar, Iram Noreen, Raed S. Alharthi, Nadeem Sarwar
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Applied Computational Intelligence and Soft Computing
Online Access:http://dx.doi.org/10.1155/2023/6661192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849683662854946816
author Maryam Munawar
Iram Noreen
Raed S. Alharthi
Nadeem Sarwar
author_facet Maryam Munawar
Iram Noreen
Raed S. Alharthi
Nadeem Sarwar
author_sort Maryam Munawar
collection DOAJ
description In today’s digital landscape, video and image data have emerged as pivotal and widely adopted means of communication. They serve not only as a ubiquitous mode of conveying information but also as indispensable evidential and substantiating elements across diverse domains, encompassing law enforcement, forensic investigations, media, and numerous others. This study employs a systematic literature review (SLR) methodology to meticulously investigate the existing body of knowledge. An exhaustive review and analysis of precisely 90 primary research studies were conducted, unveiling a range of research methodologies instrumental in detecting forged videos. The study’s findings shed light on several research methodologies integral to the detection of forged videos, including deep neural networks, convolutional neural networks, Deepfake analysis, watermarking networks, and clustering, amongst others. This array of techniques highlights the field and emphasizes the need to combat the evolving challenges posed by forged video content. The study shows that videos are susceptible to an array of manipulations, with key issues including frame insertion, deletion, and duplication due to their dynamic nature. The main limitations of the domain are copy-move forgery, object-based forgery, and frame-based forgery. This study serves as a comprehensive repository of the latest advancements and techniques, structured, and summarized to benefit researchers and practitioners in the field. It elucidates the complex challenges inherent to video forensics.
format Article
id doaj-art-d489b7051497482bbf70eb38165189c9
institution DOAJ
issn 1687-9732
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Applied Computational Intelligence and Soft Computing
spelling doaj-art-d489b7051497482bbf70eb38165189c92025-08-20T03:23:46ZengWileyApplied Computational Intelligence and Soft Computing1687-97322023-01-01202310.1155/2023/6661192Forged Video Detection Using Deep Learning: A SLRMaryam Munawar0Iram Noreen1Raed S. Alharthi2Nadeem Sarwar3Department of Computer ScienceDepartment of Computer ScienceDepartment of Computer Science and EngineeringDepartment of Computer ScienceIn today’s digital landscape, video and image data have emerged as pivotal and widely adopted means of communication. They serve not only as a ubiquitous mode of conveying information but also as indispensable evidential and substantiating elements across diverse domains, encompassing law enforcement, forensic investigations, media, and numerous others. This study employs a systematic literature review (SLR) methodology to meticulously investigate the existing body of knowledge. An exhaustive review and analysis of precisely 90 primary research studies were conducted, unveiling a range of research methodologies instrumental in detecting forged videos. The study’s findings shed light on several research methodologies integral to the detection of forged videos, including deep neural networks, convolutional neural networks, Deepfake analysis, watermarking networks, and clustering, amongst others. This array of techniques highlights the field and emphasizes the need to combat the evolving challenges posed by forged video content. The study shows that videos are susceptible to an array of manipulations, with key issues including frame insertion, deletion, and duplication due to their dynamic nature. The main limitations of the domain are copy-move forgery, object-based forgery, and frame-based forgery. This study serves as a comprehensive repository of the latest advancements and techniques, structured, and summarized to benefit researchers and practitioners in the field. It elucidates the complex challenges inherent to video forensics.http://dx.doi.org/10.1155/2023/6661192
spellingShingle Maryam Munawar
Iram Noreen
Raed S. Alharthi
Nadeem Sarwar
Forged Video Detection Using Deep Learning: A SLR
Applied Computational Intelligence and Soft Computing
title Forged Video Detection Using Deep Learning: A SLR
title_full Forged Video Detection Using Deep Learning: A SLR
title_fullStr Forged Video Detection Using Deep Learning: A SLR
title_full_unstemmed Forged Video Detection Using Deep Learning: A SLR
title_short Forged Video Detection Using Deep Learning: A SLR
title_sort forged video detection using deep learning a slr
url http://dx.doi.org/10.1155/2023/6661192
work_keys_str_mv AT maryammunawar forgedvideodetectionusingdeeplearningaslr
AT iramnoreen forgedvideodetectionusingdeeplearningaslr
AT raedsalharthi forgedvideodetectionusingdeeplearningaslr
AT nadeemsarwar forgedvideodetectionusingdeeplearningaslr