🛡️ Thread Detection AI

A machine learning-powered threat detection system using the UNSW-NB15 dataset. This project leverages explainable AI (XAI) tools such as SHAP and LIME for interpretable results and provides a user-friendly GUI built with Streamlit.

---

📊 Dataset

• Dataset Used: UNSW-NB15
• This dataset includes real modern network traffic with both normal and malicious behaviors, ideal for intrusion detection systems.

---

🚀 Features

• Preprocesses complex network logs into clean and trainable format
• Detects multiple types of network attacks
• Explainable results with SHAP and LIME
• Simple, clean UI via Streamlit for easy experimentation

---

🧠 ML & XAI Tech Stack

• Machine Learning: Scikit-learn , XAI
• XAI Tools: SHAP (Shapley values), LIME (Local Interpretable Model-Agnostic Explanations)
• GUI: Streamlit
• Language: Python 3.11

---

🛠️ Installation

1. Clone the Repository

   git clone https://github.com/thennavan-dev/Thread_Detection_AI.git
   cd Thread_Detection_AI

2. Create a virtual environment (optional but recommended)

   python -m venv venv
   source venv/bin/activate  # Linux/macOS
   venv\Scripts\activate     # Windows

3. Install Dependencies

   pip install -r requirements.txt

---

📈 How to Run

1. Run the Streamlit App

   streamlit run app.py

2. Data Preprocessing Open and run cells in Data_Processing.ipynb to clean and prepare the dataset.

3. Model Training & XAI Explore MainProject.ipynb to train the ML models and apply SHAP & LIME for explainability.

---

🤝 Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss your ideas.

---

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

---