A Tsetlin Machine-driven Intrusion Detection System for Next-Generation IoMT Security

2026-04-03

AI Summary

This study addresses the critical cybersecurity threats facing the Internet of Medical Things (IoMT) by proposing a novel intrusion detection approach based on the Tsetlin Machine—an interpretable machine learning model grounded in propositional logic. For the first time, this work applies the Tsetlin Machine to IoMT intrusion detection, achieving high accuracy while maintaining strong explainability. The method models attack patterns through human-readable logical rules and demonstrates superior performance on the CICIoMT-2024 dataset, attaining 99.5% accuracy in binary classification and 90.7% in multi-class classification, outperforming mainstream machine learning models. Decision transparency is further enhanced through clause activation heatmaps and a class-voting mechanism, which collectively provide intuitive insights into the model’s reasoning, thereby balancing robust security with interpretability.

Abstract

The rapid adoption of the Internet of Medical Things (IoMT) is transforming healthcare by enabling seamless connectivity among medical devices, systems, and services. However, it also introduces serious cybersecurity and patient safety concerns as attackers increasingly exploit new methods and emerging vulnerabilities to infiltrate IoMT networks. This paper proposes a novel Tsetlin Machine (TM)-based Intrusion Detection System (IDS) for detecting a wide range of cyberattacks targeting IoMT networks. The TM is a rule-based and interpretable machine learning (ML) approach that models attack patterns using propositional logic. Extensive experiments conducted on the CICIoMT-2024 dataset, which includes multiple IoMT protocols and cyberattack types, demonstrate that the proposed TM-based IDS outperforms traditional ML classifiers. The proposed model achieves an accuracy of 99.5\% in binary classification and 90.7\% in multi-class classification, surpassing existing state-of-the-art approaches. Moreover, to enhance model trust and interpretability, the proposed TM-based model presents class-wise vote scores and clause activation heatmaps, providing clear insights into the most influential clauses and the dominant class contributing to the final model decision.

Problem

• Intrusion Detection
• Internet of Medical Things
• Cybersecurity
• IoMT Security
• Cyberattacks

Innovation

• Tsetlin Machine
• Intrusion Detection System
• Interpretable Machine Learning
• Internet of Medical Things
• Propositional Logic