A deep transfer learning-based blockchain-assisted cooperative network architecture for internet of unmanned any vehicle things

Abstract

An Internet of Unmanned Any Vehicle Things (IUxVTs) enables cooperative operations among different unmanned vehicles, providing enhanced mission efficiency such as extended coverage, especially with the support of Internet of Things (IoT) sensors, edge computing, and dew computing. However, IUxVT communication encounters significant security and connectivity challenges. Conventional deep learning models are difficult to deploy effectively in dynamic mission environments due to their inability to adapt rapidly without extensive retraining, especially in remote areas with limited connectivity. To address these issues, this paper proposes a novel deep transfer learning (DTL)-based cooperative network architecture integrated with blockchain technology. Specifically, a lightweight blockchain and nonce-based authentication scheme were adopted to enhance protection against security threats, including spoofing, tampering, and unauthorized access. The DTL approach facilitates real-time model adaptation for IUxVTs without the need for extensive retraining, leveraging a dew computing-based delay-tolerant network for secure data storage and transmission. Experimental validation through a practical disaster rehabilitation and recovery scenario demonstrates that the proposed scheme significantly outperforms conventional methods, achieving over 97% model accuracy within fewer training epochs and reducing the training time by more than 30%. Additionally, the scheme effectively counters cybersecurity threats, showcasing robust resilience against unauthorized access and ensuring secure, low-latency data processing in dynamic and resource-constrained environments.