This project uses Machine Learning to detect Denial of Service (DoS) attacks from network traffic data.
The model was trained on the CICIDS2017 cybersecurity dataset and achieved:
- Accuracy: 99.84%
- Precision: 99.84%
- Recall: 99.84%
- F1 Score: 99.84%
- Network Traffic Analysis
- DoS Attack Detection
- Random Forest Classifier
- Feature Importance Analysis
- Confusion Matrix Visualization
- Streamlit Web Interface
Dataset Used: CICIDS2017
Records: 2.5+ Million Network Traffic Records
Features: 53 Network Traffic Features
- Python
- Pandas
- NumPy
- Scikit-Learn
- Streamlit
- Matplotlib
- Seaborn
| Metric | Score |
|---|---|
| Accuracy | 99.84% |
| Precision | 99.84% |
| Recall | 99.84% |
| F1 Score | 99.84% |
app.py
train.py
evaluate.py
requirements.txt
confusion_matrix.png
feature_importance.png
pip install -r requirements.txtRun Application:
streamlit run app.py- Real-Time Network Monitoring
- Deep Learning Models
- Explainable AI Integration
- Cloud Deployment
Ashwin Dubey is an Electronics & Communication Engineering student passionate about building intelligent software systems using Artificial Intelligence and Machine Learning.
His interests include:
- Artificial Intelligence
- Machine Learning
- AI Engineering
- Full-Stack Development
Currently focused on developing practical AI-powered applications and real-world technology solutions.