Paper Contents
Abstract
The proliferation of deepfake technology, which leverages advanced deep learning techniques to create highly realistic fake videos, poses significant threats to the integrity of digital media. This project aims to develop a robust system for detecting deepfake faces in video content, utilizing a combination of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The system is designed to accurately identify manipulated media by analyzing spatial and temporal inconsistencies in video frames. The detection model is trained on extensive datasets, including FaceForensics++, DeepFake Detection Challenge (DFDC), and Celeb-DF, ensuring high accuracy and generalizability
Copyright
Copyright © 2024 Rajat Nimje. This is an open access article distributed under the Creative Commons Attribution License.
