To address the growing challenges of road safety, efficiency, and environmental sustainability, Cooperative, Connected, and Automated Mobility (CCAM) leverages advanced communication and automation technologies across road networks. In Europe, Cooperative Intelligent Transportation Systems (C-ITS) facilitate communication among vehicles, infrastructure, and other entities, enhancing situational awareness and safety. Cooperative Awareness Messages (CAMs) provide continuous status information-such as vehicle position, speed, and direction-to nearby vehicles and infrastructure. Vehicles send CAMs to other vehicles at high frequencies ($1-10 \text{Hz}$), which, especially in dense networks, risks overloading communication channels. This may degrade network performance and potentially reduce the effectiveness of road safety applications. In this paper, we propose a new deep learning-based communication mechanism to reduce the risk of channel overload in C-ITS. Our approach enables nearby vehicles to form a temporary trust group valid for a specified period. During this period, vehicles initially send CAMs at a frequency of 1 Hz. Then, each vehicle predicts the subsequent messages of its neighbors using a variational autoencoder. Next, vehicles periodically verify the predicted CAMs by sending actual CAMs. This process ensures prediction reliability and reduces channel load by allowing vehicles to decrease CAM transmissions. We validated our approach in a simulation environment (using Omnet++, Sumo, and Artery) demonstrating its effectiveness in maintaining road safety, while reducing communication overhead.

Connected and Automated Mobility (CCAM) is undergoing a paradigm shift, with safety and efficiency increasingly dependent on connectivity. Cooperative Intelligent Transport Systems (C-ITS) support this transformation by enabling the exchange of Cooperative Awareness Messages (CAMs) between vehicles and roadside infrastructure. These messages, transmitted periodically at$\text{1 - 1 0 ~ H z}$, must be digitally signed in compliance with ETSI standards using Pseudonym Certificates (PCs). However, this security process introduces a significant overhead, as the size of the security data can be up to three times larger than the CAM payload, thereby consuming a considerable portion of the communication channel bandwidth. In this paper we propose a new authentication scheme based on deep learning. Instead of exchanging signed CAMs every time, the vehicles will authenticate each other once to establish cluster-based trust relationships, and then they will exchange only unsigned CAMs during the cluster lifetime. To ensure security within the cluster, an unsupervised variational autoencoder analyzes vehicle behavior to detect anomalies and confirm that each vehicle remains the same entity originally authenticated. Through simulations using OMNeT++, SUMO, and Artery, our method achieved a$\text{48.9 \%}$reduction in the volume of messages exchanged between vehicles, significantly decreasing communication channel overhead.

Cooperative Intelligent Transport Systems (C-ITS) are very important in our daily lives. They ensure road safety through the exchange of data between vehicles and road side units (RSU). Due to the sensitivity of the exchanged data between different entities, C-ITS systems are vulnerable to Cyber-attacks, they require high protection. In order to guarantee the integrity and the authentication of the exchanged messages, the European Telecommunications Standards Institute (ETSI), has specified specific procedures to manage certificates and signatures of all sent messages. Each vehicle periodically sends signed CAMs. Then, the integration of the signature and certificate in each transmitted CAM has a considerable impact on the communication channel load and bandwidth. In this study, we propose a new lightweight authentication mechanism which considers that vehicles on road are composed of a set of clusters having different sizes. The clusters are dynamic and change continuously. In each cluster, we implement some procedures in order to reach a trusted environment where vehicles communicate with unsigned messages when they trust their neighbours. When the trust is not guaranteed, vehicles switch to the standard communication until trust recovery. In order to reach the trust, each vehicle computes its own prediction of neighbours behavior. based on trajectory, speed. The prediction is performed using an auto-encoder running the LTSM algorithm. We have implemented this mechanisms on the OMNET++ environment and we have concluded that our mechanisms reduce the overhead generated by the authentication algorithms around 34% of the size of exchanged messages.

Cooperative Intelligent Transport Systems (C- ITS) are very important in our daily lives. They ensure road safety through the exchange of data between vehicles and road side units (RSU). Due to the sensitivity of the exchanged data between different entities, C- ITS systems are vulnerable to cyber attacks, they require high protection. In order to guarantee the integrity and the authentication of the exchanged messages, the European Telecommunications Standards Institute (ETSI), has specified specific procedures to manage certificates and signatures of all sent messages. Each vehicle periodically sends signed CAMs. Then, the integration of the signature and certificate in each transmitted CAM has a considerable impact on the communication channel load and bandwidth. In this study, we propose a new lightweight authentication mechanism which uses the cluster concept to decrease the network overhead. The objective is to reduce the number of signatures and certificates on all exchanged messages. The key idea is that neighbouring vehicles form a cluster to establish a trust relationship with each other, thus removing the need to send signed messages each time. Our method allows for the exchange of lightweight data without certificates or signatures (unsigned CAMs) and therefore verification and signature processes are no longer necessary all the time, which saves processing time and allows for smoother and faster communications.

The implementation of security in Cooperative Intelligent Transport Systems (C-ITS) is highly recommended to authenticate and ensure the integrity of Cooperative Awareness Message (CAM) exchanged between vehicles. Modern networks must be reliable and optimized in terms of the use of resources. In Europe, the ETSI standardization institute has defined a PKI (Public Key Infrastructure) for C-ITS that is used to distribute certificates for each vehicle. To ensure that CAMs (Cooperative Awareness Messages) are generated by trusted vehicles, they have to be signed using these certificates. However, integrating signature and certificate within each sent CAM presents a high impact on the overload of the communication channel and the bandwidth, due to the added size to the sent CAMs, which is significant. In this paper, we propose a new lightweight authentication protocol based on the ETSI standard. Our protocol is dynamic and integrates few concepts allowing to smartly reduce the transmitted security information, which often presents the highest cost in network systems. First, we build a cluster to establish a trusted link between vehicles giving them the opportunity to exchange information using unsigned CAMs (without integrating certificate and signature). As a result, the verification and the signing processes are not always necessary, which saves processing time and results in smoother and faster communication. Furthermore, we added a process that aims to check the consistency of the CAMs of each vehicle in the cluster in real time to avoid an attack. Under the Omnet++ simulator and the Artery framework, we have demonstrated that our protocol is more efficient in terms of communication channel usage and latency, while still secured.