Comparative study of deep learning techniques for DeepFake video detection
Deep learning addresses a wide range of complex challenges, spanning from computer vision to data analytics. It is also employed to develop softwares that pose threats to privacy and security. To develop a DeepFake video, an individual in the original video is replaced with someone else using deep learning. Various deep learning-based techniques have been proposed to detect DeepFakes. In this work, we extensively analyse DeepFake video detection techniques considering their strengths and limitations. We provide a comparative analysis along with discussing their architectures and performances. Finally, we propose hyperparameter settings that improve deep learning model’s overall accuracy and efficiency.
Authors
- Antonio Liotta (ORCID: https://orcid.org/0000-0002-2773-4421)
- Muhammad Moid Sandhu (ORCID: https://orcid.org/0000-0001-6444-0900)
- Muhammad Azfar Yaqub (ORCID: https://orcid.org/0000-0003-2150-952X)
- Imran Usman (ORCID: https://orcid.org/0000-0002-6881-7450)
- R. A. Khan
- Muhammad Sohail (ORCID: https://orcid.org/0000-0003-0284-4867)
- Mohsin Raza (ORCID: https://orcid.org/0009-0008-5630-2936)
Institutions
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Free University of Bozen-Bolzano (IT)
- Riphah International University (PK)
- University of Balochistan (PK)
- Australian e-Health Research Centre (AU)
- Balochistan University of Engineering and Technology (PK)
Publication Details
- Journal
- ICT Express
- Published
- 2024-10-09
- DOI
- https://doi.org/10.1016/j.icte.2024.09.018
- Citations
- 16
- Primary Topic
- Generative Adversarial Networks and Image Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 3.99
Funders
- Libera Università di Bolzano