Blockchain-Assisted Meta-Learning for Efficient and Reliable Authentication in IoV

Authors:

Abstract
Considering the rapid variations in a frequently changing environment and the broadcast nature of wireless signals, security authentication plays a crucial role in ensuring the security of Internet of Vehicles (IoV) communications. Existing authentication schemes in IoV suffer from two main limitations: first, protocol-based authentication causes high latency and heavy cryptographic overhead when dealing with numerous concurrent requests. Second, although edge computing-assisted methods reduce cloud communication latency, the ability to support model adaptation across environments remains limited. To address these challenges, a blockchain-assisted meta-learning (BAML) authentication scheme is proposed for providing security authentication protection in IoV. Specifically, a meta-learning algorithm is designed to collaboratively learn the device/location/channel-related feature of vehicles from source environments and then to verify their identities. During the movement of vehicles, a blockchain module is proposed to guide the new environment to inherit the most optimal authentication knowledge from the meta-learning knowledge base and achieve high performance even with limited data. The BAML scheme is designed for reliable collaboration and continuous protection in IoV. Extensive experiments are conducted to validate the effectiveness of BAML. When given 9 samples, the BAML of new environments reaches 99.7%, surpassing other competitive baselines.
Funding Information
  • National Key Research and Development Program of China (2022YFB2703000)
  • Young Backbone Teachers Support Plan of Beijing Information Science and Technology University (YBT202437)
  • Youth Academic Ability Enhancement Project of BISTU (2025QNXS15)
  • National Key Basic Research Program For Youth (2025JGYB19)