Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Survey
Qian Xu, Lei Zhang, Yixiao Liu
TL;DR
This survey advances the field of trust management in connected autonomous vehicles by proposing a novel three-layer ML-based TMS framework and a six-dimensional objective taxonomy, then detailing ML principles for each layer and evaluating ML-based methods across representative CAV scenarios. It synthesizes traditional TMS methods with modern ML approaches (including DRL, GNNs, and FL), maps them to practical data, computation, and incentive modules, and discusses open issues, privacy, and deployment challenges. The paper also offers an open repository to track up-to-date literature and projects, and outlines future directions such as multi-source data fusion, privacy-preserving ML, and cross-domain integration to enable trustworthy, resilient CAV ecosystems. Overall, the work provides a structured roadmap for researchers and practitioners aiming to implement ML-enhanced TMS in real-world CAV deployments with attention to real-time performance, scalability, and security.
Abstract
Connected Autonomous Vehicles (CAVs) operate in dynamic, open, and multi-domain networks, rendering them vulnerable to various threats. Trust Management Systems (TMS) systematically organize essential steps in the trust mechanism, identifying malicious nodes against internal threats and external threats, as well as ensuring reliable decision-making for more cooperative tasks. Recent advances in machine learning (ML) offer significant potential to enhance TMS, especially for the strict requirements of CAVs, such as CAV nodes moving at varying speeds, and opportunistic and intermittent network behavior. Those features distinguish ML-based TMS from social networks, static IoT, and Social IoT. This survey proposes a novel three-layer ML-based TMS framework for CAVs in the vehicle-road-cloud integration system, i.e., trust data layer, trust calculation layer and trust incentive layer. A six-dimensional taxonomy of objectives is proposed. Furthermore, the principles of ML methods for each module in each layer are analyzed. Then, recent studies are categorized based on traffic scenarios that are against the proposed objectives. Finally, future directions are suggested, addressing the open issues and meeting the research trend. We maintain an active repository that contains up-to-date literature and open-source projects at https://github.com/octoberzzzzz/ML-based-TMS-CAV-Survey.