In the present era of advanced technology, the Internet of Things (IoT) plays a crucial role in enabling smart connected environments. This includes various domains such as smart homes, smart healthcare, smart cities, smart vehicles, and many others.With ubiquitous smart connected devices and systems, a large amount of data associated with them is at a prime risk from malicious entities (e.g., users, devices, applications) in these systems. Innovative technologies, including cloud computing, Machine Learning (ML), and data analytics, support the development of anomaly detection models for the Vehicular Internet of Things (V-IoT), which encompasses collaborative automatic driving and enhanced transportation systems. However, traditional centralized anomaly detection models fail to provide better services for connected vehicles due to issues such as high latency, privacy leakage, performance overhead, and model drift. Recently, Federated Learning (FL) has gained significant recognition for its ability to address data privacy concerns in the IoT domain. Digital Twin (DT), proves beneficial in addressing uncertain crises and data security issues by creating a virtual replica that simulates various factors, including traffic trajectories, city policies, and vehicle utilization. However, the effectiveness of a V-IoT DT system heavily relies on the collection of long-term and high-quality data to make appropriate decisions. This paper introduces a Hierarchical Federated Learning (HFL) based anomaly detection model for V-IoT, aiming to enhance the accuracy of the model. Our proposed model integrates both DT and HFL approaches to create a comprehensive system for detecting malicious activities using an anomaly detection model. Additionally, real-world V-IoT use case scenarios are presented to demonstrate the application of the proposed model.

翻译：在当今先进技术时代，物联网在构建智能互联环境中发挥着关键作用，涵盖智能家居、智慧医疗、智慧城市、智能车辆等多个领域。随着无处不在的智能互联设备与系统普及，海量关联数据正面临系统中恶意实体（如用户、设备、应用程序）的重大威胁。云计算、机器学习与数据分析等创新技术支撑着面向车辆物联网（V-IoT）的异常检测模型开发，该领域涵盖协同自动驾驶与增强交通系统。然而，传统集中式异常检测模型因存在高延迟、隐私泄露、性能开销及模型漂移等问题，无法为网联车辆提供优质服务。近年来，联邦学习因能解决物联网领域数据隐私问题而获得广泛认可。数字孪生通过创建模拟交通轨迹、城市政策及车辆利用率等多维因素的虚拟副本，在应对不确定性危机与数据安全问题上展现出显著优势。但车辆物联网数字孪生系统的有效性高度依赖长期高质量数据的采集以做出恰当决策。本文提出一种基于分层联邦学习（HFL）的车辆物联网异常检测模型，旨在提升模型准确率。该模型融合数字孪生与分层联邦学习方法，通过构建综合系统实现基于异常检测的恶意行为识别。此外，本文还展示了真实车辆物联网使用场景案例以验证所提模型的应用价值。