SafeLink Defender is a lightweight desktop application built with Python and Tkinter to help users detect phishing URLs in real time using a machine learning model. This tool empowers individuals to verify the safety of links before clicking, helping prevent phishing attacks and other malicious activity.
- 🧠 Machine Learning-Powered: Uses a trained model (
phishing_url_model.joblib
) to detect phishing URLs. - 🌐 Real-Time URL Analysis: Paste any URL and instantly see if it's safe or suspicious.
- 🧼 Clear & Reset: Easily reset the input field and results.
- ❌ Exit Button: Quick exit from the app when done.
- 🎨 User-Friendly GUI: Built with Tkinter for a simple and clean experience.
-
Clone the Repository:
git clone https://github.com/Stanmoudev/safelink-defender.git cd safelink-defender
-
Install Dependencies:
Ensure you're using a virtual environment.pip install -r requirements.txt
If
requirements.txt
doesn't exist, manually install:pip install scikit-learn pandas joblib
-
Run the App:
python main.py
-
Using the App:
- Paste any URL into the input box.
- Click "Check URL" to analyze.
- Click "Clear" to reset the input.
- Click "Exit" to close the app.
SafeLinkDefender/
│
├── phishing_url_model.joblib # Trained ML model
├── main.py # Tkinter GUI Application
├── logo.png # App logo
├── train_url_model.py # Training script for the ML model
└── README.md # Project documentation
- scikit-learn
- joblib
- pandas
- tkinter (standard library)
- re (standard library)
- urllib (standard library)
To install all required packages:
pip install -r requirements.txt
If you wish to retrain the model:
- Download the phishing dataset.
- Run:
python train_url_model.py
This project is licensed under the MIT License - feel free to use and modify it for educational and personal projects.
Stanley Onyeka Mounagolu
Email: stanley.mou.cybersec@gmail.com
GitHub: Stanmoudev