An Intrusion Detection Mechanism for Secured IoMT Framework Based on Swarm-Neural Network

Area of Science:

• Cybersecurity in Healthcare
• Internet of Medical Things (IoMT)
• Artificial Intelligence in Medical Data Analysis

Background:

• Smart healthcare utilizes the Internet of Medical Things (IoMT) for patient monitoring.
• Data transmission in IoMT is vulnerable to attacks, risking patient privacy.
• Limited edge device resources necessitate secure remote data analysis.

Purpose of the Study:

• To propose an Empirical Intelligent Agent (EIA) using Swarm-Neural Network (Swarm-NN) for attacker identification in IoMT.
• To enhance security and accuracy of patient data analysis at the network edge.
• To address privacy leakage and network vulnerabilities in smart healthcare systems.

Main Methods:

• Development of a novel Swarm-Neural Network (Swarm-NN) model.
• Implementation of an Empirical Intelligent Agent (EIA) for threat detection.
• Evaluation using the real-time secured ToN-IoT dataset (Telemetry, Operating systems, Network data).

Main Results:

• The proposed Swarm-NN strategy accurately identifies network attacks during data transmission.
• Efficient edge-based data analysis with high accuracy is achieved.
• Achieved 99.5% accuracy on the ToN-IoT dataset, outperforming standard models.

Conclusions:

• The Swarm-NN method provides a robust solution for securing IoMT frameworks.
• The proposed approach effectively mitigates privacy risks and enhances data integrity.
• This strategy offers a significant advancement in edge-centric IoMT security.