Manuscript Title:

CNN-BASED MODEL FOR DEEPFAKE ANALYSIS USING IMAGES AND VIDEOS

Author:

RATNESH KUMAR SHUKLA, ALOK SINGH SENGAR, VINAY MISHRA, NUPA RAM CHAUHAN, SAURABH KUMAR, RAJESH KUMAR PATHAK

DOI Number:

DOI:10.5281/zenodo.12703636

Published : 2024-07-10

About the author(s)

1. RATNESH KUMAR SHUKLA - Computer Science & Engineering, Shambhunath Institute of Engineering & Technology Prayagraj, Uttar Pradesh, India.
2. ALOK SINGH SENGAR - Computer Science, School of Sciences, Noida, International University, Gautum Buddh Nagar, Uttar Pradesh, India.
3. VINAY MISHRA - School of Computer Application, Babu Banarasi Das University, Lucknow, Uttar Pradesh, India.
4. NUPA RAM CHAUHAN - Computer Science & Engineering, College of Computing Science & Information Technology, Moradabad, Uttar Pradesh, India.
5. SAURABH KUMAR - Computer Science, School of Sciences, Noida, International University, Gautum Buddh Nagar, Uttar Pradesh, India.
6. RAJESH KUMAR PATHAK - Computer Science & Engineering, GNIOT Greater Noida, Uttar Pradesh, India.

Full Text : PDF

Abstract

The convolutional neural network (CNN) is a frequently used and beneficial approach in many domains, such as computer vision, machine learning and natural language processing (NLP). CNN is used by deepfakes to modify people's photos and videos so that viewers are unable to tell the fake from the real one. Many investigations into the mechanics of deepfakes have been carried out in recent years and a variety of CNN-based methods have been introduced to identify deepfakes in photos or videos. In this research, CNN-based proposed model are implemented the deepfake analysis and face detection technologies. Furthermore, these are provided a comprehensive examination of different technologies and used in the identification of deepfake analysis. Researchers in this field will find this study useful as it covers the most recent state-of-the-art techniques for identifying deepfakes in photos or videos found in social media content. It will also facilitate comparison with previous research due to its comprehensive description of the most recent techniques employed in this field.


Keywords

CNN, Deep Learning, Facial Expression Recognition, Machine Learning and Generative Adversarial Network (GAN).