Scholarlink

<p>The rapid proliferation of the Internet of Things (IoT) has introduced a wide array of cybersecurity challenges, particularly due to the heterogeneity and resource-constrained nature of IoT devices. Centralized data storage systems, commonly employed in traditional IoT architectures, are increasingly prone to single points of failure, data breaches, and unauthorized access. Despite advancements in blockchain and machine learning, existing solutions often lack scalability, efficient threat detection, and adaptability to diverse IoT environments. To bridge this gap, we propose a novel framework that integrates a Genetic Algorithm-Optimized XGBoost (GAO-XGBoost) model with an Elliptic Curve Cryptography (ECC)-enabled blockchain architecture. In this framework, ECC ensures lightweight yet robust data encryption, while blockchain facilitates secure, immutable, and decentralized storage. The GAO-XGBoost model leverages genetic algorithms for effective feature selection, significantly improving intrusion detection performance in real-time IoT traffic scenarios. Experimental evaluation on a benchmark dataset demonstrates that the proposed system achieves 98% accuracy, a 97% true positive rate (TPR), and 97.4% recall, outperforming existing methods. This framework effectively mitigates advanced cyber threats, offering a secure, scalable, and intelligent IDS tailored for modern IoT and Industrial IoT (IIoT) networks.</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

Optimized intrusion detection and secure data management in IoT networks using GAO-Xgboost and ECC-integrated blockchain framework

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • Himanshu Nandanwar,
  • Rahul Katarya

摘要

The rapid proliferation of the Internet of Things (IoT) has introduced a wide array of cybersecurity challenges, particularly due to the heterogeneity and resource-constrained nature of IoT devices. Centralized data storage systems, commonly employed in traditional IoT architectures, are increasingly prone to single points of failure, data breaches, and unauthorized access. Despite advancements in blockchain and machine learning, existing solutions often lack scalability, efficient threat detection, and adaptability to diverse IoT environments. To bridge this gap, we propose a novel framework that integrates a Genetic Algorithm-Optimized XGBoost (GAO-XGBoost) model with an Elliptic Curve Cryptography (ECC)-enabled blockchain architecture. In this framework, ECC ensures lightweight yet robust data encryption, while blockchain facilitates secure, immutable, and decentralized storage. The GAO-XGBoost model leverages genetic algorithms for effective feature selection, significantly improving intrusion detection performance in real-time IoT traffic scenarios. Experimental evaluation on a benchmark dataset demonstrates that the proposed system achieves 98% accuracy, a 97% true positive rate (TPR), and 97.4% recall, outperforming existing methods. This framework effectively mitigates advanced cyber threats, offering a secure, scalable, and intelligent IDS tailored for modern IoT and Industrial IoT (IIoT) networks.