TOR Unmask 🚀

De-anonymizing TOR Traffic Using Machine Learning

📌 Overview

TOR (The Onion Router) enables anonymous communication, but it can also be exploited for cybercrime. TOR Unmask is a machine learning-based system that detects and classifies TOR and non-TOR network traffic using network flow analysis.

💡 Features

✅ Detects whether a network flow is from TOR or Non-TOR
✅ 98.8% accuracy using RandomForestClassifier
✅ Real-time classification with a Flask API
✅ Feature selection for optimized prediction speed
✅ React.js frontend for user-friendly testing

---

🚀 Tech Stack

• Machine Learning: Scikit-Learn, Pandas, NumPy
• Backend: Flask, Joblib, SMOTE
• Frontend: React.js
• Deployment: Flask API

---

📂 Dataset & Features

The model is trained on a dataset with 15 selected network flow features, after removing redundant ones.

📌 Selected Features:

Flow Duration, Flow Bytes/s, Flow Packets/s, Flow IAT Mean, Flow IAT Std, 
Flow IAT Max, Flow IAT Min, Fwd IAT Mean, Fwd IAT Std, Fwd IAT Max, 
Fwd IAT Min, Bwd IAT Mean, Bwd IAT Std, Bwd IAT Max, Bwd IAT Min

---

🔧 Installation & Setup

1️⃣ Clone the Repository

git clone https://github.com/TheCoderAdi/TORUnmask
cd TOR-Unmask

2️⃣ Install Dependencies

pip install -r src/requirements.txt

3️⃣ Train the Model

python src/train.py

This will save the trained model as best_model.pkl.

4️⃣ Run the Flask API

python app.py

Flask API will start at:
🔗 http://127.0.0.1:5000/predict

5️⃣ Test with cURL

Test Non-TOR Sample:

curl -X POST "http://127.0.0.1:5000/predict" -H "Content-Type: application/json" \
-d '{"features": [0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0.0, 0.2, 0.4, 0.6, 0.8, 1.0]}'

Test TOR Sample:

curl -X POST "http://127.0.0.1:5000/predict" -H "Content-Type: application/json" \
-d '{"features": [4940714, 299553.87, 363.51, 2752.49, 12223.80, 108627, -128, 4127.58, 15000.11, 108830, 3, 8105.28, 20493.49, 108808, 28]}'

---

🎯 Results & Performance

🔥 Train Accuracy: 99.95%
🎯 Test Accuracy: 98.79%
🔥 F1-Score: 96.47%
⚡ Precision: 96.78%
🔥 Recall: 96.18%

---

📜 License

This project is open-source under the MIT License.

---

📩 Contact

💬 Developer: Aditya Swayamsiddha
🔗 LinkedIn: https://www.linkedin.com/in/aditya-swayamsiddha-576ab426a/