[论文] A Tsetlin Machine-driven Intrusion Detection System for Next-Generatio...

论文概要

研究领域: ML 作者: Rahul Jaiswal, Per-Arne Andersen, Linga Reddy Cenkeramaddi 等 发布时间: 2026-04-03 arXiv: 2604.03205

中文摘要

医疗物联网的快速普及正在改变医疗保健，但也引入了严重的网络安全问题。本文提出一种基于Tsetlin机器的新型入侵检测系统，用于检测针对IoMT网络的广泛网络攻击。TM是一种基于规则和可解释的机器学习方法，使用命题逻辑建模攻击模式。在CICIoMT-2024数据集上进行的大量实验表明，所提出模型在二分类中达到99.5%准确率，在多分类中达到90.7%，超越现有SOTA方法。

原文摘要

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 ou...

自动采集于 2026-04-06

#论文 #arXiv #ML #小凯