Scholarlink

<p>The integration of Artificial Intelligence into the Industrial Internet of Things also known as the Artifical Intelligence enabled Industrial Internet of Things (AIeIIoTs) has transformed industrial operations by enabling efficient data collection, transmission, and analysis. Despite these advancements, traditional key management schemes that rely on Base Stations (BSs) as trusted intermediaries pose significant security and reliability risks. These Base Stations are vulnerable to cyberattacks, and their failure can cripple the entire AIeIIoT network. Furthermore, conventional key management approaches often place a heavy burden on AIeIIoT sensors. To address these issues, this paper introduces AIeIIoT-EKM, an innovative key management scheme designed for AIeIIoT environments that leverages blockchain technology to enhance trust and reliability. AIeIIoT-EKM eliminates the dependency on unreliable BSs by utilizing a secure, tamper-proof blockchain, thereby removing single points of failure and providing a solid foundation for secure key management. Additionally, AIeIIoT-EKM incorporates a dynamic node management algorithm to facilitate efficient key management in the evolving AIeIIoT landscape. This algorithm supports cluster formation, node integration, and revocation, ensuring continuous and secure key management across the AIeIIoT network. Extensive security analyses, simulations, and real-world testbed experiments demonstrate AIeIIoT-EKM's effectiveness in enhancing trust and reliability in AIeIIoT. The proposed scheme successfully mitigates various cyber threats, including unauthorized access, key theft, and data tampering. Moreover, AIeIIoT-EKM significantly improves reliability, evidenced by a 1.17% increase in packet delivery ratio, and reduces storage and energy consumption by 42.14% and 70%, respectively, compared to existing methods. Real-world testbed experiments further validate AIeIIoT-EKM's practical applicability, confirming its capability to bolster security and reliability in real-world AIeIIoT deployments.</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

Enhancing security and privacy in AI-driven industrial IoT with blockchain integration

  • 期刊论文

  • 发表日期：

    2025年8月22日

查看全文
  • Rishita Verma,
  • Gaurav Indra

摘要

The integration of Artificial Intelligence into the Industrial Internet of Things also known as the Artifical Intelligence enabled Industrial Internet of Things (AIeIIoTs) has transformed industrial operations by enabling efficient data collection, transmission, and analysis. Despite these advancements, traditional key management schemes that rely on Base Stations (BSs) as trusted intermediaries pose significant security and reliability risks. These Base Stations are vulnerable to cyberattacks, and their failure can cripple the entire AIeIIoT network. Furthermore, conventional key management approaches often place a heavy burden on AIeIIoT sensors. To address these issues, this paper introduces AIeIIoT-EKM, an innovative key management scheme designed for AIeIIoT environments that leverages blockchain technology to enhance trust and reliability. AIeIIoT-EKM eliminates the dependency on unreliable BSs by utilizing a secure, tamper-proof blockchain, thereby removing single points of failure and providing a solid foundation for secure key management. Additionally, AIeIIoT-EKM incorporates a dynamic node management algorithm to facilitate efficient key management in the evolving AIeIIoT landscape. This algorithm supports cluster formation, node integration, and revocation, ensuring continuous and secure key management across the AIeIIoT network. Extensive security analyses, simulations, and real-world testbed experiments demonstrate AIeIIoT-EKM's effectiveness in enhancing trust and reliability in AIeIIoT. The proposed scheme successfully mitigates various cyber threats, including unauthorized access, key theft, and data tampering. Moreover, AIeIIoT-EKM significantly improves reliability, evidenced by a 1.17% increase in packet delivery ratio, and reduces storage and energy consumption by 42.14% and 70%, respectively, compared to existing methods. Real-world testbed experiments further validate AIeIIoT-EKM's practical applicability, confirming its capability to bolster security and reliability in real-world AIeIIoT deployments.