A comprehensive machine learning system for detecting malicious URLs to protect users from phishing attacks, malware distribution, and other cyber threats.

• (In progress Project :) with continuous improvement)

• Python 3.8 or higher
• pip (Python package installer)

1. Clone the repository

   git clone <repository-url>
   cd url_classifier

2. Create and activate virtual environment

   python3 -m venv venv
   source venv/bin/activate  # On macOS/Linux
   # or
   venv\Scripts\activate     # On Windows

3. Install dependencies

   pip install -r requirements.txt

4. Start the API server

   uvicorn api:app --reload

curl -X POST http://localhost:8000/predict \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.google.com"}'

Response:

{
  "label": 0,
  "probability": 0.12
}

curl http://localhost:8000/

cd ml
python train_classifier.py

url_classifier/
├── api.py                    # FastAPI server
├── real_time_detector.py     # Real-time URL monitoring
├── ml/
│   ├── predict.py           # Traditional ML prediction
│   ├── deep_predict.py      # Deep learning prediction
│   ├── deep_learning_models.py  # LSTM and BERT models
│   ├── feature_extraction.py    # URL feature extraction
│   ├── train_classifier.py      # Model training
│   ├── model.joblib            # Trained ML model
│   ├── vectorizer.joblib       # TF-IDF vectorizer
│   └── sample_data/
│       └── data.csv            # Training dataset
└── requirements.txt

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Open a Pull Request

This project is licensed under the MIT License.

For support and questions, create an issue in the repository.

Disclaimer: This tool is for educational and research purposes. Always use in conjunction with other security measures.

working on these features:

• Multi-Model Support: Traditional ML (Logistic Regression) and Deep Learning (LSTM, BERT) models
• Real-Time Detection: Fast API endpoint for instant URL classification
• Caching System: Intelligent caching for improved performance
• Batch Processing: Support for processing multiple URLs simultaneously
• Production Ready: Includes logging, error handling, and monitoring capabilities