Scholarlink

<p>The Industrial Internet of Things (IIoT) has transformed the manufacturing landscape and advanced Industry 4.0 by creating a dynamic network of interconnected smart devices that drive digital transformation. The decentralized and evolving nature of IIoT technologies, including Industrial 5G and IoT sensors, creates a complex and vulnerable attack surface that is attractive to cybercriminals. Sophisticated and persistent multi-variant bot attacks can severely compromise these interconnected systems, making prompt and efficient detection critical. To address this challenge, we propose a novel FewShotNet with Divergence Model (FSNetM) deep learning architecture designed to protect IIoT systems against advanced multi-variant botnet attacks. The FSNetM approach was rigorously evaluated using up-to-date datasets, comprehensive performance metrics, and prevailing deep learning benchmark algorithms. Validation results demonstrate that FSNetM achieves an exceptional detection accuracy of 99.9% for multi-variant bot attacks, while maintaining rapid processing with an average detection time of 0.065&#xa0;ms, highlighting its effectiveness and efficiency in securing IIoT environments.</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

An industrial internet of things based intrusion detection using fewshotnet with divergence model

  • 期刊论文

  • 发表日期：

    2025年11月26日

查看全文
  • Pathan M. Z. Saida Khanam,
  • Sathish Kumar Kannaiah

摘要

The Industrial Internet of Things (IIoT) has transformed the manufacturing landscape and advanced Industry 4.0 by creating a dynamic network of interconnected smart devices that drive digital transformation. The decentralized and evolving nature of IIoT technologies, including Industrial 5G and IoT sensors, creates a complex and vulnerable attack surface that is attractive to cybercriminals. Sophisticated and persistent multi-variant bot attacks can severely compromise these interconnected systems, making prompt and efficient detection critical. To address this challenge, we propose a novel FewShotNet with Divergence Model (FSNetM) deep learning architecture designed to protect IIoT systems against advanced multi-variant botnet attacks. The FSNetM approach was rigorously evaluated using up-to-date datasets, comprehensive performance metrics, and prevailing deep learning benchmark algorithms. Validation results demonstrate that FSNetM achieves an exceptional detection accuracy of 99.9% for multi-variant bot attacks, while maintaining rapid processing with an average detection time of 0.065 ms, highlighting its effectiveness and efficiency in securing IIoT environments.