🛡️ Malware Detection using Machine Learning

A machine learning–powered project for detecting malware files and malicious URLs.
This repository leverages Random Forest and Logistic Regression classifiers to accurately identify malicious patterns in files and web URLs.

📖 📖 Blog Reference: Machine Learning for Malware Detection

---

🚨 Why This Project?

Traditional signature-based antivirus software struggles with:

• Polymorphic malware that changes signatures
• New malware with no known signatures
• Automated attacks by low-skilled attackers

Machine learning allows detection based on behavior and features, even for previously unseen malware.

---

🎯 Objectives

• Detect malware in executable files using PE Header analysis
• Detect malicious URLs using text-based ML methods
• Provide a terminal-based CLI interface for scanning
• Enable future enhancements like GUI and web integration

---

📂 Dataset

• PE Header Dataset: Kaggle - Malware PE Dataset
• Malicious URLs Dataset: Provided within the repo

---

🏗️ Architecture

Workflow:

1. Extract features from PE headers using pefile
2. Train Random Forest Classifier for file malware detection
3. Clean & vectorize URLs using TF-IDF
4. Train Logistic Regression for malicious URL detection
5. Apply whitelist filtering to avoid false positives

---

⚙️ Results & Performance

Model	Accuracy	Precision	Recall
Random Forest (PE Headers)	99.37%	99.20%	98.90%
Logistic Regression (URLs)	98.46%	99.18%	96.25%

ROC Curve for URL Detector

Confusion Matrix PE Header Detector

Confusion Matrix URL Detector

---

🛠️ Requirements

Install dependencies:

pip install -r requirements.txt

Main libraries:

• scikit-learn

• pandas

• numpy

• pefile

• joblib

• pyfiglet (for ASCII art in CLI)

🚀 Installation & Usage

Run Locally

git clone https://github.com/HARSH74561/Malware-Detection-using-Machine-learning.git cd Malware-Detection-using-ML pip install -r requirements.txt python main.py

Run with Docker

git clone https://github.com/HARSH74561/Malware-Detection-using-Machine-learning.git cd Malware-Detection-using-ML docker build -t py-md . docker run -ti py-md

🖥️ User Interface (CLI)

• Terminal-based interface

• ASCII art on startup

• Easy input for files and URLs

🔮 Future Enhancements

• Expand dataset for higher accuracy

• Create a GUI for Windows/Linux

• Enable real-time file scanning

• Add web-based interface for file/URL scanning

##🤝 Contributing

• Fork the repo & create a branch:

git checkout -b feature-branch

• Make your changes and commit:

git add .
git commit -m "Add new feature"

• Push and open a Pull Request:

git push origin feature-branch

About the Author

Developed by Harsh (GitHub: HARSH74561) Focused on cybersecurity, machine learning, and AI-powered tools.