Research on Dynamic Trust Management Mechanism Based on Internet of Vehicles

With the rapid development of driverless and electric vehicles, there is a growing need for vehicles to have a comprehensive understanding of road traffic conditions to enhance traffic safety. Existing vehicle trust evaluation models often struggle to adapt to the dynamic environment of vehicular networks, resulting in inaccurate trust assessments. This paper proposes a vehicle dynamic trust management framework based on Bayesian Optimization Long Short-Term Memory (BOA-LSTM) neural networks. By collecting and processing data on vehicle entity trust, historical trust, communication trust, and recommendation trust, and classifying these trust features using the fuzzy C-means algorithm, the experiment trained the BOA-LSTM model to better capture the temporal and dynamic characteristics of vehicle trust data. Experimental results demonstrate that this approach outperforms traditional models in terms of accuracy and stability. In conclusion, the proposed method significantly improves the accuracy and reliability of vehicle trust evaluation in the Internet of Vehicles (IoV), contributing to enhanced traffic safety.