🚨 Network Threat Detection as a Multi-Class Classifier Based on Feature Relevance 🚨

🔗 Overview

In today's hyper-connected world, network security is more critical than ever. This project delivers a robust multi-class classifier designed to detect and classify network threats efficiently. Using advanced Machine Learning techniques, we analyze network traffic to identify anomalies and prevent potential intrusions.

---

📊 Dataset

• Source: NSL-KDD Dataset
• A refined version of the classic KDD'99 dataset, optimized for evaluating Intrusion Detection Systems (IDS).

---

📁 Preprocessed Data & Models

Skip the preprocessing hassle! Preprocessed data and trained models are available here:

• Google Drive Link

---

👥 Team Members

• Sumeet Bapurao Khillare: skhilla@ncsu.edu
• Shashank Ajit Walke: swalke@ncsu.edu
• Raghunandan Ganesh Mante: rmante@ncsu.edu
• Soham Pravin Gundewar: sgundew@ncsu.edu

---

⚙️ Setup Instructions

1. Clone the Repository:

git clone https://github.com/SPGundewar/Network-Threat-Detection.git
cd Network-Threat-Detection

2. Download Preprocessed Data & Models: Place them in the data/ folder.
3. Install Dependencies:

pip install -r requirements.txt

4. Run Preprocessing Notebook (Optional): Update Kaggle API credentials in Preprocessing.ipynb and execute it.

---

🚀 Usage

1. Launch Jupyter Notebook:

jupyter notebook

2. Open and run the following notebooks:
   • 🛠️ Preprocessing.ipynb
   • 🤖 AutoEncoder_and_RandomForest.ipynb
   • 🌳 Decision_Tree_RandomForest.ipynb
   • 📍 KNN.ipynb

---

📂 Project Structure

Network-Threat-Detection/
├── data/                             # Preprocessed data & models
├── Preprocessing.ipynb               # Data preprocessing steps
├── AutoEncoder_and_RandomForest.ipynb# ML model implementation
├── Decision_Tree_RandomForest.ipynb  # Model analysis
├── KNN.ipynb                         # KNN analysis
├── P13_NetworkThreat_Detection.pdf   # Project report
├── requirements.txt                  # Python dependencies
└── README.md                         # Documentation

---

📈 Results

• Detailed findings and insights are documented in the project report:
  • 📑 Project Report

---

🤝 Contributing

We welcome contributions! 🚀 Feel free to fork this repository, create a pull request, and enhance the project.

---

📜 License

This project is licensed under the MIT License.

---

🙌 Acknowledgments

A big thank you to the NSL-KDD dataset creators and the open-source community for their invaluable tools and resources.

🔒 Stay Secure, Stay Safe! 🔒

📧 For queries, reach out to any team member via their listed email addresses.