Medical Data Security using Deep Learning based Key Generation, Quantum Key Exchange and Modified AES

Abstract

Medical data security refers to the protection and safeguarding of sensitive patient data in the healthcare domain. It encompasses various measures and protocols designed to ensure the confidentiality, integrity, and availability of medical information. This includes not only medical imaging data but also electronic health records (EHRs), medical test results, patient demographics, and other personally identifiable information (PII). Medical data security is of utmost importance due to several reasons like patient privacy, preventing unauthorized access or disclosure of personal health information, risk of data breaches and identity theft. This paper presents a medical data security framework using deep learning based key generation, quantum key exchange and modified Advanced Encryption Standard (AES). Deep learning-based random number generation for encryption key is an approach that utilizes deep learning models to generate secure and unpredictable sequences of numbers that can be used as encryption keys. Traditional random number generators rely on algorithms or physical processes to generate randomness. Deep learning, on the other hand, offers an alternative approach by leveraging the power of neural networks to learn patterns and generate seemingly random sequences.  This generated random number is used as key for quantum key exchange. The proposed framework uses BB84 protocol the utilizes principles of quantum mechanics to achieve secure key exchange. This ensures the confidentiality and integrity of the transmitted data. The AES algorithm is a widely used symmetric encryption algorithm that is known for its high level of security and efficiency. The conventional mix column operation is replaced with low complex algorithm for better performance.