Enhancing healthcare data security using RFE and CRHSM for big data

Area of Science:

• Computer Science
• Information Security
• Healthcare Informatics

Background:

• Medical big data security in healthcare clouds is critical but faces challenges like complexity and inefficiency.
• Existing cryptographic methods often struggle with high operational demands and storage overhead.

Purpose of the Study:

• To develop an advanced data security framework for enhancing the reliability of healthcare systems.
• To introduce a novel Cohesive Random-Hash based Security Model (CRHSM) for robust user authentication and medical record protection.

Main Methods:

• The proposed Cohesive Random-Hash based Security Model (CRHSM) integrates Squirrel Search Optimization (SSO) for random number generation during registration.
• It employs a Reformist Feistel Encryption (RFE) mechanism for encrypting medical records before cloud storage.
• The model manages system initialization, registration, login, authentication, encryption, and decryption within a hospital environment.

Main Results:

• The CRHSM model effectively secures user authentication and medical records in healthcare cloud environments.
• Performance evaluation demonstrates the model's effectiveness compared to existing security approaches.
• The framework addresses limitations of previous methods, offering improved efficiency and reduced complexity.

Conclusions:

• The novel CRHSM framework provides a reliable and efficient solution for securing medical big data in healthcare clouds.
• It enhances the overall security posture of healthcare systems by safeguarding sensitive patient information.
• The proposed model represents a significant advancement in protecting medical data against unauthorized access and attacks.