DeepFake Detection

Project Overview

This project implements multiple deep learning architectures so as to detect fake images or ai generated images. The application is built with PyTorch and Streamlit, providing an interactive web interface for users to upload and analyze images.

REFERENCES:

1. siamese net
2. xceptionet fine-tuning
3. guides

Features

• Utilizes a fine-tuned models for deepfake detection
• Interactive web interface for easy image upload and analysis
• Real-time prediction with probability scores for real and fake classifications
• Model architecture summary display
• Dataset: data

Project Structure

Installation

1. Clone the repository:

   git clone https://github.com/0xD4rky/reality-
   

2. Install the required packages:

   pip install -r requirements.txt
   

3. Run the Streamlit app:

   cd app
   

   streamlit run app.py
   

WEBSITE OVERVIEW:

License

Distributed under the MIT License. See LICENSE for more information.

Acknowledgements

• PyTorch
• Streamlit