Deepfake Detection Using Deep Learning
Leveraging AI to identify fake images.
Members: Arnav Kharbanda*, Yashasav Prajapati*, Keshav Aggarwal*
Report:- Report
COde:- Code
Description
This project focused on detecting deepfake images using state-of-the-art deep learning models and datasets like StyleGAN, Celeb-A, FFHQ, and ATTGAN. With an accuracy of approximately 70%, it showcased the potential of AI in combating fake content.
Challenges Faced
- Training models on diverse datasets to improve detection accuracy.
- Handling variations in image styles and resolutions across datasets.
- Fine-tuning deep learning architectures for optimal performance.
