Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Survey

Connected Autonomous Vehicles (CAVs) operate in dynamic, open, and multi-domain networks, rendering them vulnerable to various threats. Trust Management Systems (TMS) systematically organize the essential steps in the trust mechanism, identifying malicious nodes against both internal and external threats, while ensuring reliable decision-making for more cooperative tasks. Recent advances in machine learning (ML) offer significant potential to enhance TMS, particularly for the stringent requirements of CAVs, such as CAV nodes moving at varying speeds and exhibiting 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, comprising a trust data layer, a trust calculation layer, and a 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. The survey concludes by proposing future research directions that address open issues and align with current trends. An accompanying repository of state-of-the-art works and open-source projects is available at:https://github.com/octoberzzzzz/ML-based-TMS-CAV-Survey