YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Deepfake Image Detection Tool Using Xception Architecture
This project is a web-based Deepfake Image Detection Tool developed for Apex Broadcasting Network Ltd to verify the authenticity of digital images before publication. The system uses a deep learning model based on the Xception architecture to accurately distinguish between real and manipulated images.
Features
- Image upload and deepfake detection
- Xception-based deep learning detection engine
- Confidence score for each prediction
- Deepfake literacy and awareness content
- Secure image handling with CSRF protection and rate limiting
Technology Stack
- Backend: Python (Flask)
- Frontend: HTML, CSS, JavaScript
- Deep Learning Model: Xception (TensorFlow/Keras)
- Security: CSRF protection, rate limiting, secure headers
Project Structure
app.py– Flask backend and detection logictemplates/index.html– User interfacestatic/– Images and frontend assetsbest_xception_model_finetuned.keras– Trained modeluploads/– Temporary image storage
How to Run Locally
pip install -r requirements.txt
python app.py
"# deepfake-tool"
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://waleeyd/deepfake_tool")