Scholarlink

<p>In recent years, the increasing connectivity in the Internet of Vehicles (IoV) has raised critical concerns regarding secure authentication and intrusion detection. The proposed methodology presents a Blockchain-based IoV Authentication Model integrated with a Deep Learning-based authorized participant detection to address these challenges. Leveraging the decentralized and tamper-proof nature of blockchain technology, the system assigns each vehicle a unique cryptographic identity, securely recorded on the blockchain to prevent unauthorized access and identity spoofing. It ensures a reliable and immutable authentication process across the network. To further enhance the security infrastructure, a deep learning-based authorized participant detection is embedded within the blockchain storage framework to detect unauthorized users in real time. The authorized participant detection is built using Lightweight Deep Dense Recurrent Model (LDDRM), which balances computational efficiency and detection accuracy. The performance of the LDDRM is further improved through the integration of an Adaptive Grouper Moray Eel (AGrME) Optimization Algorithm, which fine-tunes the model’s loss function for optimal learning and threat detection. The combined approach strengthens the IoV ecosystem by providing robust, intelligent, and scalable security solutions. In addition, the proposed framework is designed to support large-scale vehicular networks with low authentication latency and reduced computational overhead through the use of lightweight deep learning inference and consortium blockchain-based consensus.</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

Secure authentication protocol for internet of vehicles using blockchain based authorized user detection

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月12日

查看全文
  • Vijay Kumar Tiwari,
  • Prashant Kumar

摘要

In recent years, the increasing connectivity in the Internet of Vehicles (IoV) has raised critical concerns regarding secure authentication and intrusion detection. The proposed methodology presents a Blockchain-based IoV Authentication Model integrated with a Deep Learning-based authorized participant detection to address these challenges. Leveraging the decentralized and tamper-proof nature of blockchain technology, the system assigns each vehicle a unique cryptographic identity, securely recorded on the blockchain to prevent unauthorized access and identity spoofing. It ensures a reliable and immutable authentication process across the network. To further enhance the security infrastructure, a deep learning-based authorized participant detection is embedded within the blockchain storage framework to detect unauthorized users in real time. The authorized participant detection is built using Lightweight Deep Dense Recurrent Model (LDDRM), which balances computational efficiency and detection accuracy. The performance of the LDDRM is further improved through the integration of an Adaptive Grouper Moray Eel (AGrME) Optimization Algorithm, which fine-tunes the model’s loss function for optimal learning and threat detection. The combined approach strengthens the IoV ecosystem by providing robust, intelligent, and scalable security solutions. In addition, the proposed framework is designed to support large-scale vehicular networks with low authentication latency and reduced computational overhead through the use of lightweight deep learning inference and consortium blockchain-based consensus.