Quantum-Safe Digital Twin Authentication for ML-Driven Early Disease Detection in Healthcare Systems

Area of Science:

• Healthcare technology
• Artificial intelligence in medicine
• Cybersecurity in healthcare

Background:

• Smart healthcare services like disease detection and patient monitoring face significant privacy and security challenges.
• Sensitive health data requires robust protection within the evolving digital healthcare ecosystem.

Purpose of the Study:

• To propose a secure digital twin-enabled machine learning (ML) framework for disease detection.
• To enhance patient privacy and enable secure real-time health data synchronization and risk identification.

Main Methods:

• Developed a digital twin framework integrating ML-based disease detection with a privacy-preserving environment.
• Implemented a lattice-based authentication scheme for quantum threat resistance.
• Conducted experiments to evaluate authentication and ML detection robustness, including white-box attack simulations.

Main Results:

• The proposed framework enables secure synchronization of real-time patient data to digital twins for health monitoring.
• Experimental results validate the robustness of the lattice-based authentication and ML disease detection.
• White-box attack experiments highlight the critical need for a secure data pipeline to prevent model collapse.

Conclusions:

• A secure digital twin framework with quantum-resistant authentication is effective for ML-based disease detection.
• Ensuring data pipeline security from collection to processing is vital for maintaining model integrity and patient data protection.