Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects

In recent years, rapid advancements in deepfakes (incorporating Artificial Intelligence (AI), machine, and deep learning) have updated tools and techniques for manipulating multimedia. Though technology has primarily been utilized for beneficial purposes, such as education and entertainment, it is a...

Full description

Saved in:
Bibliographic Details
Main Authors: Naveed Ur Rehman Ahmed, Afzal Badshah, Hanan Adeel, Ayesha Tajammul, Ali Daud, Tariq Alsahfi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10816641/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841557043314425856
author Naveed Ur Rehman Ahmed
Afzal Badshah
Hanan Adeel
Ayesha Tajammul
Ali Daud
Tariq Alsahfi
author_facet Naveed Ur Rehman Ahmed
Afzal Badshah
Hanan Adeel
Ayesha Tajammul
Ali Daud
Tariq Alsahfi
author_sort Naveed Ur Rehman Ahmed
collection DOAJ
description In recent years, rapid advancements in deepfakes (incorporating Artificial Intelligence (AI), machine, and deep learning) have updated tools and techniques for manipulating multimedia. Though technology has primarily been utilized for beneficial purposes, such as education and entertainment, it is also used for malicious or unethical tasks to spread disinformation or ruin someone’s dignity, even if it encompasses harassing and blackmailing victims. Deepfakes refer to high-quality and realistic multimedia-manipulated content that has been digitally modified or synthetically generated. We conducted a systematic literature review of deepfake detection to offer an updated overview of existing research work that initially describes the widely accessible deepfake generation tools, classifications, and detection process. We highlighted recent techniques in visual deepfake detection based on the feature representations, grouped into four domains: spatial, temporal, frequency, and spatio-temporal, including their key features and limitations by providing details of existing datasets, together with the potentials of deepfake and its future directions. This study tried to add an updated repository of technological change in deepfake, which could help researchers to develop robust deepfake models.
format Article
id doaj-art-c4869578eeb0480ca984a92b12fd7523
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c4869578eeb0480ca984a92b12fd75232025-01-07T00:01:39ZengIEEEIEEE Access2169-35362025-01-01131923196110.1109/ACCESS.2024.352328810816641Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future ProspectsNaveed Ur Rehman Ahmed0Afzal Badshah1https://orcid.org/0000-0002-3444-4609Hanan Adeel2Ayesha Tajammul3Ali Daud4https://orcid.org/0000-0002-8284-6354Tariq Alsahfi5https://orcid.org/0000-0003-4299-1626Department of Computing, Hamdard University, Islamabad Campus, Islamabad, PakistanDepartment of Software Engineering, University of Sargodha, Sargodha, PakistanDepartment of Computing, Hamdard University, Islamabad Campus, Islamabad, PakistanU.S.-Pakistan Center for Advanced Studies in Water, Mehran University of Engineering and Technology, Jamshoro, Sindh, PakistanFaculty of Resilience, Rabdan Academy, Abu Dhabi, United Arab EmiratesDepartment of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi ArabiaIn recent years, rapid advancements in deepfakes (incorporating Artificial Intelligence (AI), machine, and deep learning) have updated tools and techniques for manipulating multimedia. Though technology has primarily been utilized for beneficial purposes, such as education and entertainment, it is also used for malicious or unethical tasks to spread disinformation or ruin someone’s dignity, even if it encompasses harassing and blackmailing victims. Deepfakes refer to high-quality and realistic multimedia-manipulated content that has been digitally modified or synthetically generated. We conducted a systematic literature review of deepfake detection to offer an updated overview of existing research work that initially describes the widely accessible deepfake generation tools, classifications, and detection process. We highlighted recent techniques in visual deepfake detection based on the feature representations, grouped into four domains: spatial, temporal, frequency, and spatio-temporal, including their key features and limitations by providing details of existing datasets, together with the potentials of deepfake and its future directions. This study tried to add an updated repository of technological change in deepfake, which could help researchers to develop robust deepfake models.https://ieeexplore.ieee.org/document/10816641/Deepfake detectionmachine learningdeep learningdeepfake applicationsdeepfake datasetsdeepfake generation tools
spellingShingle Naveed Ur Rehman Ahmed
Afzal Badshah
Hanan Adeel
Ayesha Tajammul
Ali Daud
Tariq Alsahfi
Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
IEEE Access
Deepfake detection
machine learning
deep learning
deepfake applications
deepfake datasets
deepfake generation tools
title Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
title_full Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
title_fullStr Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
title_full_unstemmed Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
title_short Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
title_sort visual deepfake detection review of techniques tools limitations and future prospects
topic Deepfake detection
machine learning
deep learning
deepfake applications
deepfake datasets
deepfake generation tools
url https://ieeexplore.ieee.org/document/10816641/
work_keys_str_mv AT naveedurrehmanahmed visualdeepfakedetectionreviewoftechniquestoolslimitationsandfutureprospects
AT afzalbadshah visualdeepfakedetectionreviewoftechniquestoolslimitationsandfutureprospects
AT hananadeel visualdeepfakedetectionreviewoftechniquestoolslimitationsandfutureprospects
AT ayeshatajammul visualdeepfakedetectionreviewoftechniquestoolslimitationsandfutureprospects
AT alidaud visualdeepfakedetectionreviewoftechniquestoolslimitationsandfutureprospects
AT tariqalsahfi visualdeepfakedetectionreviewoftechniquestoolslimitationsandfutureprospects