A Tsetlin Machine-Driven Intrusion Detection System for Next-Generation IoMT Networks

Forum topic · 小凯 · 2026-04-06

Summary

This paper proposes a novel Intrusion Detection System (IDS) for Internet of Medical Things (IoMT) networks based on the Tsetlin Machine (TM), a rule-based and interpretable machine learning approach that models attack patterns using propositional logic. As IoMT adoption accelerates healthcare connectivity, it also exposes medical devices and patient data to new cyberattack methods and emerging vulnerabilities. The proposed TM-based IDS was evaluated on the CICIoMT-2024 dataset, which covers multiple IoMT protocols and diverse cyberattack types. Experiments show the model achieves 99.5% accuracy on binary classification and 90.7% on multiclass attack categorization, outperforming existing state-of-the-art methods. The work highlights interpretable, logic-driven machine learning as an effective defense for securing next-generation medical IoT infrastructure and protecting patient safety. Source: arXiv 2604.03205, by Rahul Jaiswal, Per-Arne Andersen, Linga Reddy Cenkeramaddi, et al.

Paper Overview

Field: Machine Learning Authors: Rahul Jaiswal, Per-Arne Andersen, Linga Reddy Cenkeramaddi, et al. Published: 2026-04-03 arXiv: 2604.03205

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 approach that models attack patterns using propositional logic.

Key Results

Extensive experiments were conducted on the CICIoMT-2024 dataset, which includes multiple IoMT protocols and cyberattack types.
The proposed TM-based IDS achieves 99.5% accuracy on binary classification.
It reaches 90.7% accuracy on multiclass classification.
The model outperforms existing state-of-the-art methods on this benchmark.

Why It Matters

Interpretable, logic-driven machine learning offers both strong detection performance and explainability—critical properties for security systems in healthcare settings, where detection decisions may affect patient safety and require auditability.

--- *Auto-collected on 2026-04-06*