Scholarlink

<p>The rapid growth of Industrial Internet of Things (IIoT) networks has created new cybersecurity risks that traditional centralized intrusion detection systems can’t handle because they can’t scale up, protect privacy, or work in environments with limited resources. This study introduces a lightweight, blockchain-enabled federated intrusion prevention platform. Our research integrates three fundamental concepts: (i) a Proof-of-Trust (PoT) agreement mechanism specifically designed for IIoT devices with limited resources, replacing traditional consensus algorithms that use a lot of processing power; (ii) Byzantine fault-tolerant trust management that can keep the system’s integrity even with up to 33% malicious participants; and (iii) an integrated communication optimization strategy that combines model quantization and gradient sparsification. The system helps find strange behavior at the edge, keeps trust via blockchain, and trains models with federated learning while keeping privacy. Extensive experiments on four benchmark datasets (ToN-IoT, UNSW-NB15, CIC-IDS-2017, and a custom IIoT dataset with 1.25 million records) show that this approach works better than others: it has a 97.8% detection accuracy, a 1.2% false positive rate, an average response time of 85 ms, and an 80% reduction in communication overhead. This work presents the inaugural architecture for the integration of blockchain-based trust management and federated learning, specifically tailored for resource-constrained IIoT contexts, hence introducing a novel paradigm for integrated cybersecurity while preserving data sovereignty.</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

A lightweight blockchain-enabled federated intrusion prevention framework for resource-constrained industrial IoT devices to detect and mitigate emerging cyberattacks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月29日

查看全文
  • Dinesh Kumar Nishad,
  • Rashmi Singh,
  • Saifullah Khalid

摘要

The rapid growth of Industrial Internet of Things (IIoT) networks has created new cybersecurity risks that traditional centralized intrusion detection systems can’t handle because they can’t scale up, protect privacy, or work in environments with limited resources. This study introduces a lightweight, blockchain-enabled federated intrusion prevention platform. Our research integrates three fundamental concepts: (i) a Proof-of-Trust (PoT) agreement mechanism specifically designed for IIoT devices with limited resources, replacing traditional consensus algorithms that use a lot of processing power; (ii) Byzantine fault-tolerant trust management that can keep the system’s integrity even with up to 33% malicious participants; and (iii) an integrated communication optimization strategy that combines model quantization and gradient sparsification. The system helps find strange behavior at the edge, keeps trust via blockchain, and trains models with federated learning while keeping privacy. Extensive experiments on four benchmark datasets (ToN-IoT, UNSW-NB15, CIC-IDS-2017, and a custom IIoT dataset with 1.25 million records) show that this approach works better than others: it has a 97.8% detection accuracy, a 1.2% false positive rate, an average response time of 85 ms, and an 80% reduction in communication overhead. This work presents the inaugural architecture for the integration of blockchain-based trust management and federated learning, specifically tailored for resource-constrained IIoT contexts, hence introducing a novel paradigm for integrated cybersecurity while preserving data sovereignty.