The Malware Detection System is a Machine Learning-based web application that analyzes executable files and predicts whether they are Malware or Benign. The project leverages a trained Random Forest Classifier and integrates threat intelligence services to provide real-time security insights through an interactive Streamlit dashboard.
This application provides:
- Malware/Benign prediction using Machine Learning
- VirusTotal threat intelligence integration
- File hash generation (MD5 & SHA256)
- Feature importance visualization
- PDF security report generation
- Scan history tracking and analytics
- Malware Detection using Machine Learning
- File Hash Generation (MD5 & SHA256)
- VirusTotal Threat Intelligence Integration
- Feature Importance Visualization
- PDF Security Report Generation
- Scan History Dashboard
- Interactive Data Visualizations
Algorithm: Random Forest Classifier
- File Size
- Entropy
- Number of Sections
- Suspicious API Calls
- Network Connections
- Registry Modifications
- File Operations
- Process Injections
- DLL Loads
- Suspicious Strings
- Python
- Streamlit
- Scikit-learn
- Pandas
- NumPy
- Plotly
- ReportLab
- VirusTotal API
Malware-Detection-System/
├── streamlit_app.py
├── Random_Forest_model.pkl
├── scaler.pkl
├── requirements.txt
├── screenshots/
└── README.md
pip install -r requirements.txt
streamlit run streamlit_app.py
- SHAP Explainable AI Integration
- Malware Family Classification
- Cloud Deployment
- Real-time Threat Monitoring
Omm Miriyala B.Tech CSE (Data Science)