Federated Learning in Healthcare 🏥 using Elliptic Curve Cryptography (ECC) for Secure Weight Transfer

📋 Overview

This project explores the use of Federated Learning (FL) in healthcare, focusing on Elliptic Curve Cryptography (ECC) for secure neural network weight transfer between federated nodes. The research highlights enhanced data privacy, reduced inference time, and is currently being prepared for publication.

⚙️ Key Features

• Data Privacy: No patient data leaves the local healthcare nodes.
• Security: ECC for secure weight transfers in the FL process.
• Efficiency: Emphasis on reducing inference time in real-time healthcare applications.

🛠️ Technologies Used

• Languages:
  • C/C++
  • Python
• Libraries:
  • Crypto++: For implementing ECC.
  • Flower: For Federated Learning coordination.

📊 Results

The project focuses on optimizing:

• Inference Time: Faster model predictions.
• Secure Aggregation: Efficient and safe weight transfer across nodes.

Results attached in the repository for reference.

🚀 Installation

Clone the repository:

git clone https://github.com/your-repo/federated-learning-healthcare.git

🔮 Future Work

• Further optimizing ECC performance.
• Extending to other healthcare datasets.
• Publishing the results.

🤝 Contributing

Contributions are welcome! Please follow the standard GitHub flow.

📄 License

This project is licensed under the MIT License.