IoT-based external attacks aware secure healthcare framework using blockchain and SB-RNN-NVS-FU techniques.

Area of Science:

• Computer Science
• Information Security
• Healthcare Technology

Background:

• Internet of Things (IoT) applications are increasingly used in healthcare, processing sensitive user data on cloud servers.
• IoT healthcare networks face significant security vulnerabilities, posing risks to patient data integrity and privacy.

Purpose of the Study:

• To propose a novel, secure Electronic Health Record (EHR) framework specifically designed for Internet of Things (IoT) healthcare environments.
• To enhance the security and reliability of patient data management within IoT-enabled healthcare systems.

Main Methods:

• Implemented a trust evaluation and node clustering using Tasmanian Devil Optimization (TDO) with Student's T-Distribution.
• Employed Transposition Cipher-Squared Elliptic Curve Cryptography (TCS-ECC) for data encryption, followed by hashing and blockchain integration.
• Utilized Swish Beta activated-Recurrent Neural Network (SB-RNN) for attack detection and Neutrosophic Vague Set Fuzzy (NVS-Fu) for double-spending attack identification.

Main Results:

• Achieved a security level of 98% and an accuracy of 98% in attack classification.
• Reduced attack detection time to 1300 ms, demonstrating significant performance improvements.
• Experimental analysis confirmed the proposed model's reliability and superior performance compared to existing methods.

Conclusions:

• The proposed secure EHR framework effectively addresses security threats in IoT healthcare.
• Experimental results validate the efficiency and robustness of the implemented security measures.