Scholarlink

<p>The paper introduces an innovative security framework using Blockchain technology and deep learning in securing patient monitoring and health data transmission with IoT, for the safety of devices in smart healthcare systems. The proposed system uses Blockchain and its distributed ledger that records all transactions related to a particular asset which can guarantee integrity, transparency, and non-repudiation of IoT device data via an immutable log. To improve security, deep learning and more specifically, convolutional neural network (CNN) is used to detect anomalies within the IoT network through device behaviour and data flow patterns analysis. Our experiments on a comprehensive healthcare testbed with multiple sensors attest to the high efficacy of the current approach in differentiating between normal and adversarial behaviour. Lastly, the performance of the proposed approach is validated and compared with existing recent studies based on metrics such as attack estimation rate (AER %) and accuracy (%), The results demonstrate that the proposed approach outperforms existing studies in terms of performance.</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

Designing a Blockchain-integrated security system with deep learning for IoT-based healthcare data protection

  • 期刊论文

  • 发表日期：

    2025年7月15日

查看全文
  • Mili Srivastava,
  • Sunil Kumar,
  • Rabins Porwal,
  • Sameer Yadav,
  • Balraj Kumar,
  • Ashish Kaushal,
  • Vikas Lamba

摘要

The paper introduces an innovative security framework using Blockchain technology and deep learning in securing patient monitoring and health data transmission with IoT, for the safety of devices in smart healthcare systems. The proposed system uses Blockchain and its distributed ledger that records all transactions related to a particular asset which can guarantee integrity, transparency, and non-repudiation of IoT device data via an immutable log. To improve security, deep learning and more specifically, convolutional neural network (CNN) is used to detect anomalies within the IoT network through device behaviour and data flow patterns analysis. Our experiments on a comprehensive healthcare testbed with multiple sensors attest to the high efficacy of the current approach in differentiating between normal and adversarial behaviour. Lastly, the performance of the proposed approach is validated and compared with existing recent studies based on metrics such as attack estimation rate (AER %) and accuracy (%), The results demonstrate that the proposed approach outperforms existing studies in terms of performance.