Vehicle platoon offers numerous benefits in terms of road safety, energy efficiency, and traffic management in urban freight delivery. Privacy preservation is critical here: location information ties to customer confidentiality and reputation guarantees platoon reliability, yet most existing platoon management schemes fail to preserve privacy while achieving vehicle location-matching. Meanwhile, traditional distance calculation methods such as Euclidean distance are unsuitable for urban road layouts, and most schemes assume member vehicles must follow to unified endpoints, a rigid constraint conflicting with the scenario's needs. In this paper, we propose a privacy-preserving platoon management scheme for flexible platoon splitting in urban freight delivery (PPFPS). In detail, the PPFPS scheme leverages location and reputation to achieve flexible platoon splitting in platoon management while preserving vehicle privacy. Specially, we design an encrypted Manhattan distance calculation method (EMC) by combining bloom filters and Paillier cryptosystem, which is tailored to the road layouts in urban environments and deployed on cloud servers. The EMC method enables privacy-preserving location matching to achieve flexible platoon splitting, and reputation is used to ensure the reliability of vehicle platoon. Furthermore, the EMC method significantly minimizes the involvement of the trusted authority by introducing cloud-assisted approaches. Theoretical analysis demonstrates that the PPFPS scheme effectively preserves privacy and defends a variety of potential attacks. Simulation evaluation confirms that the PPFPS scheme supports more functions while significantly reducing computation overheads by 66.59% to 78.72% on the TA side, and maintains communication overheads of the similar order of magnitude as the existing schemes.

As a crucial component of intelligent transportation systems, Vehicular Ad Hoc Networks (VANETs) are increasingly exposed to severe cybersecurity threats, particularly hybrid attacks such as Denial of Service (DoS), black hole attacks, and Sybil identity spoofing. In high-density traffic environments, Road Side Units (RSUs) often suffer from heavy loads, which limits their responsiveness and accuracy in attack detection. To address this issue, this paper proposes a UAV-assisted intelligent multi-attack detection model. By introducing unmanned aerial vehicles (UAVs) as mobile auxiliary nodes, the model dynamically offloads traffic monitoring and data processing tasks from RSUs, thereby alleviating resource bottlenecks. Building on this, a hybrid detection architecture is designed that combines Convolutional Neural Networks (CNN) and Deep Q-Networks (DQN). The CNN is employed to extract spatiotemporal traffic features, including vehicle port traffic density, node forwarding rate distributions, and identity activity levels, while convolutional filters capture potential abnormal patterns. The DQN further optimizes attack detection through Q-learning-based decision making. The simulation results demonstrate that the proposed method outperforms existing approaches in detecting diverse types of attack, significantly improving detection accuracy and reducing response latency.

To address the limits of current three-dimensional unmanned aerial vehicles trajectory privacy methods in semantic modeling, social relation analysis, and privacy-utility balance, this paper proposes a new method that combines semantic features and social strength. A semantic model based on spatial location and flight behavior is built to detect key points like takeoff and landing and identify flight phases. Bi-directional Long Short-Term Memory is used to model time features, and Hidden Markov Model is used to improve the results. A multi-dimensional social strength system is then designed to measure the relation between trajectories by combining variation and conflict analysis. A trajectory generation model based on conditional Generative Adversarial Network is also built. The generator combines semantic embedding, graph attention, and Transformer to model dynamic features and adds differential privacy noise. The discriminator evaluates the output from three sides: realness, semantic consistency, and social compliance. Experiments show that this method improves both data usability and privacy protection.

On vehicular named data network (VNDN), Interest Flooding Attack (IFA) can exhaust the computing resources by sending a large number of malicious Interest packets, which leads to the failure of satisfying the legitimate requests and seriously hazards the operation of Internet of Vehicles (IoV). To solve this problem, this paper proposes a distributed network traffic monitoring-enabled multi-indicator detection and prevention approach for VNDN to detect and resist the IFA attacks. In order for facilitating this approach, a distributed network traffic monitoring layer based on road side unit (RSU) is constructed. With such a monitoring layer, a multi-indicator detection approach is designed, which consists of three indicators: information entropy, self-similarity, and singularity, whereby the thresholds are tweaked by the real-time density of traffic flow. Apart from the detection, a blacklisting based prevention approach is realized to mitigate the attack impact.We validate the proposed approach via prototyping it on our VNDN experimental platform using realistic parameters setting and leveraging the original NDN packet structure to corroborate the usage of the required Source ID for identifying the source of the Interest packet, which consolidates the practicability of the approach. The experimental results show that our multi-indicator detection approach has a greatly higher detection performance than those of using indicators individually, and the blacklisting-based prevention can effectively mitigate the attack impact as well.

With the popularity of the global positioning system (GPS) and mobile Internet, a large amount of vehicle trajectory data has been generated and applied in intelligent transportation systems. The collected trajectory data often contains sensitive user information, which poses a risk of user privacy disclosure. To enhance the privacy of vehicle trajectory data, this article proposes a novel two-layer privacy preserving (TLPP) mechanism that leverages clustering features. Initially, density-based clustering is employed to derive regional attributes and density characteristics of trajectory points. Subsequently, a generative adversarial network (GAN) incorporating a long short-term memory (LSTM) network is utilized to learn the distribution of clustered trajectories, facilitating the generation of synthetic trajectories. These synthetic trajectories are then substituted for the original trajectories, constituting the first layer of privacy protection. To ensure the fidelity of the synthetic data, a novel generator loss function is designed, utilizing the Wasserstein distance to quantify the spatial similarity between the real and synthetic trajectories. Furthermore, to accommodate the personalized privacy requirements, a tailored differential privacy mechanism is introduced. This mechanism provides a second layer of privacy protection by introducing the region-specific perturbations to the data. The experimental results show that, compared with the other models, our approach can effectively protect the user privacy while ensuring the trajectory data utility.