Scholarlink

<p>A blockchain-driven approach is presented to ensure robust authentication and private data distribution in Vehicular Ad Hoc Networks (VANETs). A primary objective to develop a robust authentication procedure using an Adaptive Echo State Network (AESNet) and a dual trapdoor homomorphic encryption method (DTHE-OMK) to enhance secure data transmission in VANETs. This work employs a combination of optimization strategies, including the Position Updated Enhanced Frilled Lizard Optimization (PUE-FLO) algorithm, to fine-tune the parameters of the AESNet for node authentication. The authentication analysis on accuracy provided results in the range of 6.323% of CWO-AESNet, 5.828% of TOT-AESNet, 8.353% of WOA-AESNet, 6.323% of FLO-AESNet for the optimization algorithms and 7.838% of DNN, 4.729% of LSTM, 4.248% of GRU, and 4.729% of ESNet for various literature models, respectively. This work concludes that the developed approach improves both integrity and safety of information shared across VANETs.</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

Blockchain-enabled secure authentication and privacy-preserving information sharing in VANETs using adaptive echo state networks and dual trapdoor homomorphic encryption

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月3日

查看全文
  • Poonguzhali Ilango,
  • Nagarajan Sivarajan,
  • M. P. Rajakumar,
  • Sumanth Venugopal

摘要

A blockchain-driven approach is presented to ensure robust authentication and private data distribution in Vehicular Ad Hoc Networks (VANETs). A primary objective to develop a robust authentication procedure using an Adaptive Echo State Network (AESNet) and a dual trapdoor homomorphic encryption method (DTHE-OMK) to enhance secure data transmission in VANETs. This work employs a combination of optimization strategies, including the Position Updated Enhanced Frilled Lizard Optimization (PUE-FLO) algorithm, to fine-tune the parameters of the AESNet for node authentication. The authentication analysis on accuracy provided results in the range of 6.323% of CWO-AESNet, 5.828% of TOT-AESNet, 8.353% of WOA-AESNet, 6.323% of FLO-AESNet for the optimization algorithms and 7.838% of DNN, 4.729% of LSTM, 4.248% of GRU, and 4.729% of ESNet for various literature models, respectively. This work concludes that the developed approach improves both integrity and safety of information shared across VANETs.