Exploring Various Deep Learning Techniques for DeepFake Video Classification
A.Nymisha Nandini Reddy
, B.Hemalatha , Neha Saw , Vikram Kumar , Bhaskar Das
Deepfake, Convolutional Neural Network(CNN),Deep Learning, Transfer Learning
The rapidly developing use of deepfake technology affects digital media credibility and public trust.Deepfakes are created using advanced machine learning techniques, such as generative adversarial networks (GANs) and variational autoencoders (VAEs), to produce highly realistic synthetic images, videos, and audio by manipulating original media​.The current study develops a powerful deepfake video detection system using advanced deep learning algorithms. We fine-tuned three CNN architectures—InceptionResNetV2, EfficientNetB5, and VGG16—using around 5GB of data from the Kaggle Deepfake Detection Challenge dataset. Transfer learning improved our models' efficiency and performance. This study emphasizes the necessity for a robust deepfake detection technique. Future research will center on full-body deepfake detection and real-time capabilities for enhanced digital media authentication.
"Exploring Various Deep Learning Techniques for DeepFake Video Classification", JNRID - JOURNAL OF NOVEL RESEARCH AND INNOVATIVE DEVELOPMENT (www.JNRID.org), ISSN:2984-8687, Vol.2, Issue 5, page no.a248-a253, May-2024, Available :https://tijer.org/JNRID/papers/JNRID2405029.pdf
Volume 2
Issue 5,
May-2024
Pages : a248-a253
Paper Reg. ID: JNRID_700350
Published Paper Id: JNRID2405029
Downloads: 000358
Research Area: Science and Technology
Country: Hyderabad, Telangana, India
ISSN: 2984-8687 | IMPACT FACTOR: 9.57 Calculated By Google Scholar | ESTD YEAR: 2023
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: JNRID (IJ Publication) Janvi Wave
