GenConVit+: Advanced hybrid framework for deepfake detection for safeguarding digital media integrity

Authors

  • Mithun B. Patil N.K. Orchid College of Engineering and Technology, Solapur
  • Vijay A. Sangolgi N.K. Orchid College of Engineering and Technology, Solapur
  • Vipul V. Bag N.K. Orchid College of Engineering and Technology, Solapur
  • Abdul Basit Patwegar N.K. Orchid College of Engineering and Technology, Solapur
  • Rohini Koli N.K. Orchid College of Engineering and Technology, Solapur
  • Aafra Naikwadi N.K. Orchid College of Engineering and Technology, Solapur
  • Abdul Gani Shaikh N.K. Orchid College of Engineering and Technology, Solapur

DOI:

https://doi.org/10.62110/sciencein.jist.2024.v12.820

Keywords:

Deep Learning , DeepFake detection, Computer Vision Transformer, 3D CNN, Hybrid models, Convolutional Neural Network (CNN)

Abstract

The propagation of deepfake videos has introduced serious concerns, particularly in their potential to Circulate misleading details and undermine the integrity of digital media. In response to this challenge, we present the Generative Convolutional Vision Transformer (GenConViT) as a robust solution for deepfake video detection. GenConViT integrates the strengths of ConvNeXt and Swin Transformer models with 3D Convolutional neural network (CNN) to extract relevant features. It further harnesses the capabilities of Autoencoders and Variational Autoencoders to discern patterns in latent data distribution. Our model’s proficiency is validated through rigorous training and evaluation on four distinct datasets. DFDC, FF++, DeepFakeTIMIT, and Celeb-DF (v2). The results speak volumes, with GenConViT achieving notably high classification accuracy, F1 Scores, and AUC values. It rises to the challenge of generalizability in deepfake detection by effectively differentiating a wide spectrum of falsified videos while upholding the integrity of digital media. On average, the GenConViT model attains an accuracy of 95.6% and an impressive AUC value of 99.3% across the datasets we examined. This underscores its capacity to robustly detect deepfake content and maintain the integrity of digital media.
URN:NBN:sciencein.jist.2024.v12.820

Downloads

Download data is not yet available.

Author Biographies

  • Mithun B. Patil, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

  • Vijay A. Sangolgi, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

  • Vipul V. Bag, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

  • Abdul Basit Patwegar, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

  • Rohini Koli, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

  • Aafra Naikwadi, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

  • Abdul Gani Shaikh, N.K. Orchid College of Engineering and Technology, Solapur

    Department of Artificial Intelligence and Data Science

deepfake detection in images using CNN

Downloads

Published

2024-03-04

Issue

Section

Computer Sciences and Mathematics

URN

How to Cite

GenConVit+: Advanced hybrid framework for deepfake detection for safeguarding digital media integrity. (2024). Journal of Integrated Science and Technology, 12(5), 820. https://doi.org/10.62110/sciencein.jist.2024.v12.820

Similar Articles

1-10 of 106

You may also start an advanced similarity search for this article.