Robust trust management in Intelligent Transportation System: A machine learning approach

Intelligent Transportation Systems (ITS) are revolutionising modern mobility by leveraging advancements in 5G technology, smart sensors, and sophisticated data analytics. These advancements facilitate the exchange and decision making of information in real time, improving safety and efficiency. However, the heterogeneous and loosely connected nature of the ITS components presents significant challenges in evaluating and managing trust within the ecosystem. Traditional approaches, such as blockchain-based consensus mechanisms, peer-to-peer voting systems, and static rule-based trust models, struggle to evaluate trust uniformly across diverse components and data types in real time, leaving the system vulnerable to various threats. Recent studies explored Machine Learning (ML) techniques to address trust management in ITS. These advanced approaches offer promising solutions for processing large volumes of heterogeneous data, identifying complex patterns, and adapting to dynamic environments. However, most existing ML-based solutions focus on assessing trust for particular components, such as vehicles and roadside units (RSUs), rather than addressing the collective trust of the entire ITS ecosystem. This paper proposes a novel ML-based dynamic trust management system termed MLT. It employs a feedforward neural network and the Levenberg–Marquardt Algorithm to dynamically assess the trustworthiness of ITS components. The system incorporates a dynamic time decay factor and continuously updates the trust scores, allowing effective identification and isolation of malicious actors. Through extensive simulations, MLT outperforms baseline models by up to 10% in precision and 9% in F-measure across various attack scenarios. These results highlight the superior performance of MLT in accuracy and robustness compared to existing trust management models.