False emergency messages, a critical variant of False Data Injection Attacks (FDIAs) in Vehicular Ad Hoc Networks (VANETs), pose severe threats to traffic safety and undermine the reliability of intelligent transportation systems. Existing detection approaches often rely on macroscopic traffic models to validate the reported incidents. However, such models overlook the localized driving behaviors and fail to capture fine-grained dependencies between vehicles and events. To overcome these limitations, we introduce a spatio-temporal detection framework based on Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks. The GCN component learns spatial interactions among vehicles relative to a reported incident, while the LSTM models the temporal dynamics of their behavioral evolution. Extensive simulations show that our framework consistently outperforms state-of-the-art baselines, demonstrating the importance of microscopic, context-aware traffic modeling for reliable FDIA detection in dynamic VANET environments.

Accurate environmental perception is crucial for the safe and efficient navigation of autonomous vehicles. Integrating data from various sensors, such as cameras, radars, and lidars, presents challenges due to differing sensor reliability and environmental conditions. This study introduces a new method for combining data from multiple sensors using evidence theory (Dempster-Shafer), which helps to address uncertainties and conflicting information. By dynamically merging sensor inputs and resolving conflicts, our model improves object detection and classification in uncertain situations. Through extensive simulations and detailed analyses using metrics like Belief (Bel), Plausibility (Pl), Confidence Interval (CI), and Pignistic Probability (P), the study confirms the effectiveness and dependability of this fusion approach for practical autonomous vehicle applications.

The implication of cyber-physical systems into industrial processes has introduced some security breaches due to the lack of security mechanisms. This article aims to come up with a novel methodology to detect false data injection attacks on cyber-physical systems. To reach this goal, we propose an efficient anomaly-based approach for detecting false data injection attacks against industrial cyber-physical systems. Particularly, we use sequential pattern mining techniques, which are commonly used for learning most important patterns of a system. In our case, the frequent pattern learning algorithm is used to create a database corresponding to the normal operation of the system, then, this database is fed into an attack detection algorithm in order to alert the user whenever an attack is occurring. The extensive simulations prove that our attack detection approach is able to detect attacks with a great accuracy and that this methodology could work even for large scale systems.

Cyber-physical industrial systems are internet-enabled physical entities embedded with computers and control components consisting of sensors and actuators. However, inter-connecting the cyber and physical spaces led to new security challenges. This paper presents a recovery controller based on a physics-informed neural network (PINN) to enhance the resilience of cyber-physical systems (CPS) against false data injection attacks (FDIA). The PINN-based controller is trained to predict corrective actions that can restore the desired operating conditions of the CPS after an attack. The proposed approach is validated on a quadruple water tank process, a benchmark system for CPS control. Results show that the PINN-based recovery controller can effectively restore the system's desired operating conditions, outperforming conventional recovery controllers that do not incorporate the physical dynamics of the CPS in their design.

Several works are aiming to develop techniques allowing detecting False Data Injection Attacks, which represents one of the most harmful attacks due to its ability to damage a Cyber Physical Systems (CPS). Among these techniques the watermarking represents one of the most used ones. This paper proposes the design of a False Data Injection Attack (FDIA) against a CPS protected by a watermark-based detector. The attack herein proposed is achieved in two phases. The first one is a passive phase, where the adversary builds a black box model of the system. Then, he uses the already built model to create the FDIA without being detected by the watermark based detector. The extensive simulations prove that this attack could be used to deceive the system even with the presence of a dynamic watermark.

This paper presents an improved version of Contention Based Forwarding (CBF) protocol, the current standardized dissemination protocol in VANETs by the ETSI, referred to as iCBF. iCBF address two main issues exhibited by the original CBF: (1) the high dissemination delay induced by the adopted intermittent re-transmission paradigm, and (2) the low message coverage capability due to the use of an indiscriminate inhibition rule of the relay candidates. The high delay problem has been mitigated by enabling a continuous re-transmissions process at the application layer, thanks to the use of one new sender-oriented relay selection mechanism to regulate the next dissemination entities at the sender side. In order to overcome some intrinsic VANETs challenges, especially the high speed vehicles, we exploit the original CBF's forwarding algorithm (with a slight modification) to monitor the explicitly selected relays and compensate for the unexpected message loss. The poor message coverage problem has been tackled through introducing a tridant concept, designed to adjust the relay selection and inhibition rules for ensuring an effective distribution of relays inside the targeted dissemination area. As respect to the original CBF, iCBF evaluation shows significant performance improvements in terms of messages coverage and transmission delay while not wasting the limited channel resources and bringing compliant with ETSI-GeoNetworking standard.

Smart cities are a wide range of projects made to facilitate the problems of everyday life and ensure security. Our interest focuses only on the Intelligent Transport System (ITS) that takes care of the transportation issues using the Vehicular Ad-Hoc Network (VANET) paradigm as its base. VANETs are a promising technology for autonomous driving that provides many benefits to the user conveniences to improve road safety and driving comfort. VANET is a promising technology for autonomous driving that provides many benefits to the user's conveniences by improving road safety and driving comfort. The problem with such rapid development is the continuously increasing digital threats. Among all these threats, we will target the Sybil attack since it has been proved to be one of the most dangerous attacks in VANETs. It allows the attacker to generate multiple forged identities to disseminate numerous false messages, disrupt safety-related services, or misuse the systems. In addition, Machine Learning (ML) is showing a significant influence on classification problems, thus we propose a behavior-based classification algorithm that is tested on the provided VeReMi dataset coupled with various machine learning techniques for comparison. The simulation results prove the ability of our proposed mechanism to detect the Sybil attack in VANETs.

Misbehavior detection in VANETs is critical to provide security and road safety since the communication between vehicles is directly affected by attackers’ messages. A new misbehavior detection approach is presented and compared with previous approaches. The estimated angle of arrival and the estimated distance using path loss model are proposed as new features to use for detection mechanism. When an attacker sends a message, it can produce false position values. Therefore, using a set of suitable features about the relation between sender and receiver will help to detect attackers. Machine learning techniques, Random Forest and k-Nearest Neighbor, are implemented to classify a vehicle as an attacker or not by considering the proposed features. The performance of the proposal is evaluated using a public dataset and easily compared to others. The results show that the proposed approach increases the performance of misbehavior detection in terms of classification evaluation metrics.

The implication of Cyber-Physical Systems (CPS) in critical infrastructures (e.g., smart grids, water distribution networks, etc.) has introduced new security issues and vulnerabilities to those systems. In this paper, we demonstrate that black-box system identification using Support Vector Regression (SVR) can be used efficiently to build a model of a given industrial system even when this system is protected with a watermark-based detector. First, we briefly describe the Tennessee Eastman Process used in this study. Then, we present the principal of detection scheme and the theory behind SVR. Finally, we design an efficient black-box SVR algorithm for the Tennessee Eastman Process. Extensive simulations prove the efficiency of our proposed algorithm.

Heterogeneity is one of the main issues for the deployment of the Industry 4.0. This is due to the diversity in the available robots and the IIoT devices. These equipments use different programming languages and communication protocols. To make the integration of such equipments easy, we propose TalkRoBots, a middleware that allows heterogeneous robots and IIoT devices to communicate together and exchange data in a transparent way. The middleware was experimented in a real scenario with different robots that demonstrate its efficiency.

Cooperative Intelligent Transport Systems (C-ITS) are expected to play an important role in our lives. They will improve the traffic safety and bring about a revolution on the driving experience. However, these benefits are counterbalanced by possible attacks that threaten not only the vehicle's security, but also passengers' lives. One of the most common attacks is the Sybil attack, which is even more dangerous than others because it could be the starting point of many other attacks in C-ITS. This paper proposes a distributed approach allowing the detection of Sybil attacks by using the traffic flow theory. The key idea here is that each vehicle will monitor its neighbourhood in order to detect an eventual Sybil attack. This is achieved by a comparison between the real accurate speed of the vehicle and the one estimated using the V2V communications with vehicles in the vicinity. The estimated speed is derived by using the traffic flow fundamental diagram of the road's portion where the vehicles are moving. This detection algorithm is validated through some extensive simulations conducted using the well-known NS3 network simulator with SUMO traffic simulator.

Vehicular ad-hoc network (VANET) is a special type of wireless mobile ad-hoc network. Generally, communication between vehicles and fixed roadside units (RSUs) are used in Intelligent Transportation Systems (ITS) to allow vehicles updating their knowledge about the traffic status. However, the deployment of fixed RSU is expensive and it needs a long time to be achieved. To overcome this issue, we study a cost-efficient solution based on the deployment of some specific mobile RSUs. An analytical study is proposed to analyse the enhancement of the communication probability when considering mobile RSUs compared with the classical approach with fixed RSUs. The results show that the introduction of a rate of 5% of mobile RSUs can double the communication probability.

In this paper, we consider the identification problem of stochastic and deterministic stochastic Petri nets (PNs). The approach herein proposed consists of inferring a PN structure and identifying its parameters. Hence, the first step leads to the synthesis of a PN structure with the measurable sequence of events and states. This approach determines the measurable part and estimates the nonmeasurable part of the PN to be established. Once both parts are obtained, the PN structure and the initial marking of the nonmeasurable places are obtained thanks to the integer linear programming technique. In the second step of this approach, the parameters of the obtained model are estimated. Stochastic and deterministic stochastic PNs with deterministic and exponentially distributed transition durations are considered. A systematic identification method is proposed based on event sequences that are recorded by supervision systems. This method is based on a Markov model whose state space is isomorphic to the reachability graph of the untimed PN model.