This is a DGA (Domain Generation Algorithm) detection system based on RNN (Recurrent Neural Network). The system can automatically identify whether a domain name is maliciously generated by DGA.
- RNN model for domain classification
- Real-time domain detection
- Pre-trained model available
- Training process visualization
- High accuracy detection results
The training dataset consists of two parts:
- Malicious domains generated by DGA
- Legitimate domains
You can download the complete dataset from Google Drive.
- Python 3.7+
- PyTorch
- pandas
- matplotlib
- scikit-learn
- Clone the repository
git clone https://github.com/yourusername/dga-detection.git
cd dga-detection
- Install dependencies
pip install -r requirements.txt
- Download the dataset and place it in the
data
directory
- Train the model
python main.py
- Predict domains
python predict.py
.
├── data/ # Data directory
├── main.py # Main program
├── model.py # Model definition
├── trainer.py # Trainer
├── predict.py # Prediction script
├── utils.py # Utility functions
└── data_loader.py # Data loader
MIT License
Pull requests and issues are welcome.
Please submit an issue if you have any questions.