A Hybrid AI-Driven Post-Quantum Encryption Framework for Secure Medical Data Transmission in IoMT Systems

Abstract

The rapid digitization of healthcare system operations and the widespread adoption of Internet of Medical Things (IoMT) devices has created an explosion in the amount of sensitive medical data, which has made them a target for cyberattacks. Thus, providing secure transmission and storage of Electronic Health Records (EHRs) is one of the most significant challenges facing the modern healthcare infrastructure. To address this issue, this paper presents a Hybrid Artificial Intelligence based Post-Quantum Encryption System (HAPES) framework for secure encryption and decryption of medical data. This proposed framework contains many types of Multi-Layered Encryption Algorithms, including AES-256 for data confidentiality, Elliptic Curve Cryptography (ECC) for efficient key exchange and Post-Quantum Cryptographic (PQC) Algorithms to ensure future security. Additionally, there will be an Artificial Intelligence based Anomaly Detection Module to identify potential cyber threats in real-time, and a Blockchain Layer to provide Tamper-Proof Data Integrity and Secure Audit Trails. Also included in HAPES is the Zero-Trust Security Model to provide Continuous Authentication and Authorization of Users. Experimental results show an improvement in Security Strength, Encryption Time, and Resistance to Cyber Threats compared with traditional encryption technologies. In summary, HAPES provides a scalable and efficient means to secure healthcare data in the Cloud and IoMT environments.