In vehicular ad hoc networks (VANETs), vehicles broadcast emergency messages and beacon messages, which enable drivers to perceive traffic conditions beyond their visual range thus improve driving safety. However, internal attackers can launch a false message attack for selfish purposes by reporting a non-existent traffic incident in emergency messages. Moreover, some collusion attackers may spread bogus beacon messages cooperatively to make the bogus traffic incident more deceptive. To improve the accuracy of false emergency message detection, we propose a novel intrusion detection system (IDS) based on time series classification and deep learning. Considering that traffic parameters are highly correlated with time, we collect time series of traffic parameters closely related to traffic incidents from messages of vehicles near reported traffic incidents as time series feature vectors. To recognize the pattern of traffic parameters changing over time more accurately, a traffic incident classifier based on long short-term memory (LSTM) is designed and trained using time series feature vectors from both normal and collusion attack scenarios. Based on the classification result, the authenticity of the emergency message can be determined. Finally, we evaluate the performance of the proposed LSTM-based IDS through extensive simulation. Simulation results validate that our IDS is more accurate in false message detection compared with some well-known machine learning-based schemes.

In the Internet of Vehicles (IoV), data privacy concerns have prompted the adoption of Federated Learning (FL). Efficiency improvements in FL remain a focal area of research, with recent studies exploring model pruning to lessen both computation and communication overhead. However, in the IoV, model pruning presents unique challenges and remains underexplored. Pruning strategy design is critical as it directly impacts each vehicle's learning latency and capacity to participate in FL. Furthermore, FL performance and model pruning are intricately connected. Additionally, the fluctuating number and mobility states of vehicles per round complicate determining the optimal pruning ratio, closely intertwining pruning with vehicle selection. This study introduces Vehicular Federated Learning with Adaptive Model Pruning (VFed-AMP) to tackle these challenges by integrating adaptive pruning with dynamic vehicle selection and resource allocation. We analyze the impact of pruning ratios on learning latency and convergence rate. Then, guided by these findings, a joint optimization problem is formulated to maximize the convergence rate concerning optimal vehicle selection, bandwidth allocation, and pruning ratios. Finally, a low-complexity algorithm for joint adaptive pruning and vehicle scheduling is proposed to address this problem. Through theoretical analysis and system design, VFed-AMP enhances FL efficiency and scalability in the IoV, offering insights into optimizing FL performance through strategic model adjustments. Numerical results on various datasets show VFed-AMP achieves superior training accuracy (e.g., at least 13.4% improvement for BelgiumTS) and significantly reduces training time (e.g., at least up to 1.8x for CIFAR-10) compared to traditional FL methods.

Vehicular crowdsensing (VCS) has emerged as a promising paradigm, in which spatio-temporal-based sensing tasks are outsourced to intelligent connected vehicles (ICVs) carrying sensor-equipped devices. A critical issue of VCS is to guarantee the spatio-temporal sensing coverage by assigning tasks to appropriate vehicles, which inevitably requires vehicles’ precise locations or trajectories and thus raises location privacy concerns. To address this problem, we propose a novel secret sharing-based efficient privacy-preserving task allocation scheme for VCS, which can select sensing vehicles with approximately optimal total spatio-temporal coverage based on their future trajectories while achieving strong location privacy preservation for users (customers and sensing vehicles). With a grid-based region encoding method, a user’s location information is encoded as a binary array, termed as the region code. Based on the idea of secret sharing, we design a bit-wise XOR-based secret splitting method to split a user’s region code into two random shares and separately transmit them to two fog servers, thereby perfectly hiding the original location information. With a carefully-designed code permutation mechanism and a greedy task allocation algorithm, the cloud server and fog servers can efficiently collaborate and complete task allocation based on permuted region codes without revealing users’ location information. Detailed security analysis shows that our proposed scheme effectively preserves users’ location privacy. Extensive experiments conducted on a realistic traffic scenario data set also demonstrate that it is efficient in communication and computation while achieving large total spatio-temporal coverage.

The proliferation of intelligent connected vehicles (ICVs) has catalyzed the emergence of vehicular crowdsensing (VCS) applications, wherein sensing tasks are assigned to ICVs with abundant sensing resources and high mobility. To select workers whose future trajectories have sufficient spatio-temporal similarity with the target sensing area, workers unavoidably need to upload their trajectories to the VCS platform that is not fully trusted, thereby triggering location privacy concerns. Recently, numerous privacy-preserving worker selection schemes have been put forth. Nevertheless, they either fail to enable flexible arbitrary query ranges or incur substantial communication and computation costs, which severely limits their suitability for VCS applications. To tackle the above two issues simultaneously, we propose a novel efficient and privacy-preserving VCS worker selection scheme that supports flexible arbitrary spatial ranges. By utilizing the Bloom filter technique and lightweight cryptographic tools, our proposed scheme allows the VCS platform to efficiently collaborate with the fog server to compute the spatio-temporal similarity without leaking location-derived Bloom filters. Rigid security analysis shows that our scheme effectively preserves the location privacy of both workers and the query user. Extensive experiments are conducted and the results demonstrate that our scheme is significantly more efficient in both communication and computation compared with the state-of-the-art scheme.

Vehicular crowdsensing (VCS) leverages data exchange among intelligent connected vehicles (ICVs) to support diverse intelligent applications, making privacy protection essential due to the sensitivity of shared data. Federated learning (FL) combined with differential privacy (DP) has emerged as a powerful approach for safeguarding privacy in such distributed systems. Due to the unique characteristics of vehicular networks, many VCS tasks are inherently linked to spatial and temporal factors. This article focuses on these VCS tasks within the context of a complex system, where ICV mobility serves as a central factor that dynamically influences interconnected aspects such as task matching accuracy, participation rates, and DP noise consistency. The multifaceted impact of ICV mobility on these elements requires a comprehensive analysis to understand its cascading effects on privacy protection and model performance within FL-based VCS. To address these complexities, we propose DFed-ADP, a dynamic FL framework with an adaptive DP mechanism tailored for VCS. DFed-ADP includes a rigorous theoretical derivation to quantify the influence of ICV mobility on the DP noise scale and a dynamic ICV selection strategy that prioritizes data importance and adapts to mobility patterns. Specifically, we introduce an adaptive user-level DP and derive a closed-form expression to quantify the impact of ICV mobility on noise variance. Then, based on theoretical analysis, we propose an efficient ICV selection scheme that ensures participating ICVs can provide high-value data and complete training tasks on time. These designs ensure a robust balance between privacy and model performance. Experimental results demonstrate the adaptability and efficiency of DFed-ADP, achieving significant accuracy improvements under independent and identically distributed (IID) and non-IID settings in VCS.

In practical deployments of decentralized federated learning (FL) in Internet of Things (IoT) environments, the non-independent and identically distributed (Non-IID) nature of client-local data limits model performance. Furthermore, concept drift further exacerbates complexity and introduces temporal uncertainty that significantly degrades convergence and generalization. Existing approaches, which mainly rely on model-level similarity or static clustering, struggle to disentangle inherent data heterogeneity from dynamic distributional shifts, resulting in poor adaptability under drift scenarios. This paper proposes FedPLC, a novel FL framework that introduces two mechanism-level innovations: (i) Prototype-Anchored Representation Learning (PARL), a strategy inspired by Learning Vector Quantization (LVQ) that stabilizes the representation space against label noise and distributional shifts by aligning sample embeddings with class prototypes; and (ii) Label-wise Dynamic Community Adaptation (LDCA), a fine-grained adaptation mechanism that dynamically reorganizes classifier heads at the label level, enabling rapid personalization and drift-aware community evolution. Together, PARL and LDCA enable FedPLC to explicitly disentangle static Non-IID heterogeneity from temporal concept drift, achieving robust and fine-grained adaptation for large-scale IoT/edge client populations. Our experimental results on the Fashion-MNIST, CIFAR-10, and SVHN datasets demonstrate that FedPLC outperforms the state-of-the-art federated learning methods designed for concept drift in both abrupt drift and incremental drift scenarios.