Securing healthcare data: A federated learning framework with hybrid encryption in cluster environments

Area of Science:

• Computer Science
• Cybersecurity
• Health Informatics

Background:

• Healthcare data is highly sensitive and requires robust protection.
• Existing encryption methods may face challenges with scalability, interoperability, and regulatory compliance (HIPAA).
• Cluster environments present unique security challenges for distributed healthcare data.

Purpose of the Study:

• To develop and evaluate a hybrid encryption scheme combining Elliptic Curve Cryptography (ECC) and the Serpent algorithm.
• To assess the scheme's suitability for safeguarding healthcare data in cluster environments.
• To ensure scalability, interoperability, and HIPAA compliance for the proposed solution.

Main Methods:

• Developed a hybrid encryption scheme integrating ECC for key management and Serpent for symmetric encryption.
• Implemented a hierarchical key management strategy with ECC for secure key exchange.
• Utilized regular key rotation and storage practices aligned with HIPAA regulations.
• Built a Python framework to implement and test the encryption scheme.

Main Results:

• The ECC-Serpent hybrid encryption scheme demonstrated enhanced security and performance for healthcare data.
• The solution proved scalable and interoperable within cluster environments.
• The implemented framework achieved a 97.5% accuracy rate in safeguarding patient data.
• The scheme ensures compliance with HIPAA regulations.

Conclusions:

• The ECC-Serpent hybrid encryption is a viable and effective solution for securing healthcare data in cluster environments.
• The approach balances efficient key distribution with high encryption strength.
• This method enhances data integrity, patient privacy, and regulatory adherence in healthcare.