This project was developed as part of a machine learning assignment to build a Cybersecurity Risk Detector. The aim was to classify and detect potential cybersecurity threats using custom-generated datasets and machine learning algorithms. The project culminates in a local web application for real-time risk prediction.
The project tackles a classification problem to determine the presence or absence of cybersecurity risks. The dataset was custom-generated using Python and saved as veri.csv
.
- Dataset Creation:
- Generated synthetic data (
veri.csv
) using Python and stored the code inveri.ipynb
.
- Generated synthetic data (
- Model Training:
- Trained the dataset using 10 different machine learning algorithms.
- Selected the best-performing algorithm based on Accuracy.
- Saved the best model as
eniyi.joblib
.
- Web Application Development:
- Designed a local web application using Streamlit.
- Integrated the trained model (
eniyi.joblib
) for real-time predictions.
- Project Demonstration:
- A demonstration video link showcasing the working application is provided in
link.text
.
- A demonstration video link showcasing the working application is provided in
- Custom dataset generation.
- Evaluation of multiple ML algorithms.
- Streamlit-based web application for risk detection.
- Best model saved for reuse.
- Programming Language: Python
- Libraries:
- Scikit-learn (ML algorithms)
- Pandas, NumPy (data processing)
- Matplotlib (visualization)
- Streamlit (web application)
- Model Serialization: joblib
- Version Control: Git
- Clone the repository:
git clone https://github.com/dirshaye/Cybersecurity_Risk_Detector.git
- Navigate to the project directory:
cd dirshaye-cyber_security_risk_detector
- Install the dependencies:
pip install -r requirements.txt
- Ensure the dataset (
veri.csv
) is in the root directory. - To train models and select the best one:
python app.py
- Launch the web application:
streamlit run app.py
- Access the application in your browser and test predictions.
└── dirshaye-cyber_security_risk_detector/
├── algoritma.ipynb # Notebook for evaluating algorithms
├── app.py # Streamlit application script
├── eniyi.joblib # Best-performing ML model
├── link.text # Video demonstration link
├── veri.csv # Generated dataset
└── veri.ipynb # Notebook for dataset generation
This project is licensed under the MIT License.
For any questions or feedback, feel free to reach out:
- GitHub: dirshaye