Scholarlink

<p>The rapid expansion of Internet of Things (IoT) networks has introduced complex security challenges, particularly for Intrusion Detection Systems (IDS). Traditional IDS methods often struggle with centralized vulnerabilities, data privacy, and the detection of sophisticated cyberattacks. This research addresses these issues by proposing a Hybrid Blockchain-Based Framework that leverages advanced cryptographic techniques and machine learning models. The framework integrates Elliptic Curve Cryptography (ECC), the Digital Signature Algorithm (DSA), and SHA-512 to enhance data privacy, authentication, and integrity. A novel Self-Adaptive Differential Evolution (SADE) algorithm is introduced to optimize cryptographic key generation, particularly in resource-constrained environments. The Practical Byzantine Fault Tolerance (PBFT) consensus algorithm ensures system resilience and prevents centralized failures, while the InterPlanetary File System (IPFS) provides secure off-chain data storage. Furthermore, the Genetic Algorithm (GA) optimizes IDS performance by refining detection rules, and an XGBoost-based model is designed to effectively identify intrusions within heterogeneous IoT networks. The blockchain component demonstrates a latency of 0.342&#xa0;s, a throughput of 67 transactions per second, and a network overhead of 1.69&#xa0;MB. The XGBoost model achieves an accuracy of 98.12%, an F1 score of 97.98%, a False Positive Rate (FPR) of 2.24%, and a False Negative Rate (FNR) of 2.19%. Comparative analysis with existing models demonstrates the superior accuracy and robustness of the proposed framework. This research fills a critical gap in IoT security by providing a comprehensive solution that enhances the effectiveness, scalability, and resilience of IDS in the face of evolving cyber 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

A hybrid Blockchain-Based framework for securing intrusion detection systems in internet of things

  • 期刊论文

  • 发表日期：

    2025年7月31日

查看全文
  • Himanshu Nandanwar,
  • Rahul Katarya

摘要

The rapid expansion of Internet of Things (IoT) networks has introduced complex security challenges, particularly for Intrusion Detection Systems (IDS). Traditional IDS methods often struggle with centralized vulnerabilities, data privacy, and the detection of sophisticated cyberattacks. This research addresses these issues by proposing a Hybrid Blockchain-Based Framework that leverages advanced cryptographic techniques and machine learning models. The framework integrates Elliptic Curve Cryptography (ECC), the Digital Signature Algorithm (DSA), and SHA-512 to enhance data privacy, authentication, and integrity. A novel Self-Adaptive Differential Evolution (SADE) algorithm is introduced to optimize cryptographic key generation, particularly in resource-constrained environments. The Practical Byzantine Fault Tolerance (PBFT) consensus algorithm ensures system resilience and prevents centralized failures, while the InterPlanetary File System (IPFS) provides secure off-chain data storage. Furthermore, the Genetic Algorithm (GA) optimizes IDS performance by refining detection rules, and an XGBoost-based model is designed to effectively identify intrusions within heterogeneous IoT networks. The blockchain component demonstrates a latency of 0.342 s, a throughput of 67 transactions per second, and a network overhead of 1.69 MB. The XGBoost model achieves an accuracy of 98.12%, an F1 score of 97.98%, a False Positive Rate (FPR) of 2.24%, and a False Negative Rate (FNR) of 2.19%. Comparative analysis with existing models demonstrates the superior accuracy and robustness of the proposed framework. This research fills a critical gap in IoT security by providing a comprehensive solution that enhances the effectiveness, scalability, and resilience of IDS in the face of evolving cyber threats.