Scholarlink

<p>The Industrial Internet of Things (IIoT) is a fast-expanding field of technology that radically transforms the industrial environment into an automated one. Network stream data offers a constant stream of real-time data from numerous sensors and devices, which is essential in IIoT systems. Assailants can more readily access network stream data when there is network automation, making network data collection more susceptible. For effective data analytics, we have to identify the counteract cyber threats. To gain relevant insights from this data, Intrusion Detection Systems (IDS) are required. To address this issue, the Automated Intrusion Detection Framework (AIDF)” is developed for network drift adaption in IIoT systems. This framework has a Window-based Weighted Ensemble (WWE) model with optimized feature selection using Whale Optimization. The effectiveness of the suggested framework for real-time network intrusion detection is evaluated using a dataset from both the real world and static. The proposed framework outperforms well compared to the state-of-the-art methods. This is applicable in several sectors, including banking, healthcare, and transportation, which&#xa0;may use the suggested framework to improve their cyber security posture and protect themselves from online threats.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Real-Time Intrusion Detection in IIoT Stream Data Using Window-Based Weighted Ensemble Techniques

  • 期刊论文

  • 发表日期：

    2025年1月7日

查看全文
  • N. Malathy,
  • A. Thana Swvtha,
  • T. Bharathi Leela,
  • Apoorva Raaman

摘要

The Industrial Internet of Things (IIoT) is a fast-expanding field of technology that radically transforms the industrial environment into an automated one. Network stream data offers a constant stream of real-time data from numerous sensors and devices, which is essential in IIoT systems. Assailants can more readily access network stream data when there is network automation, making network data collection more susceptible. For effective data analytics, we have to identify the counteract cyber threats. To gain relevant insights from this data, Intrusion Detection Systems (IDS) are required. To address this issue, the Automated Intrusion Detection Framework (AIDF)” is developed for network drift adaption in IIoT systems. This framework has a Window-based Weighted Ensemble (WWE) model with optimized feature selection using Whale Optimization. The effectiveness of the suggested framework for real-time network intrusion detection is evaluated using a dataset from both the real world and static. The proposed framework outperforms well compared to the state-of-the-art methods. This is applicable in several sectors, including banking, healthcare, and transportation, which may use the suggested framework to improve their cyber security posture and protect themselves from online threats.