Cooperative Intelligent Transport Systems (C-ITS) is an advanced technology for road safety and traffic efficiency over Vehicular Ad Hoc Networks (VANETs) allowing vehicles to communicate with other vehicles or infrastructures. The security of VANETs is one of the main concerns in C-ITS because there may be some attacks in such type of network that may endanger the safety of the passengers. Intrusion Detection Systems (IDS) play an important role to protect the vehicular network by detecting misbehaving vehicles. In general, the works in the literature use the same well-known features in a centralized IDS. In this paper, we propose a Machine Learning (ML) mechanism that takes advantage of three new features, which are mainly related to the sender position, allowing to enhance the performances of IDS for position falsification attacks. Besides, it presents a comparison of two different ML methods for classification, i.e. k-Nearest Neighbor (kNN) and Random Forest (RF) that are used to detect malicious vehicles using these features. Finally, Ensemble Learning (EL) which combines different ML methods, in our case kNN and RF, is also carried out to improve the detection performance. An IDS is constructed allowing vehicles to detect misbehavior in a distributed way, while the detection mechanism is trained centrally. The results demonstrate that the proposed mechanism gives better results, in terms of classification performance indicators and computational time, than the best previous approaches on average.

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.

This paper proposes a middleware called TalkRoBots that handles interoperability issues, which could be encountered in Industry 4.0. The latter proposes a unified communication approach facilitating the collaboration between heterogeneous equipment without needing to change neither the already used software nor the existing hardware. It allows heterogeneous robots, using both open and proprietary robotic frameworks (i.e., ROS, ABB, Universal Robots, etc.), to communicate and to share information in a transparent manner. It allows robots and Industrial Internet of Things (IIoT) devices to communicate together. Furthermore, a resilience mechanism based on an Artificial Intelligence (AI) approach was designed in order to allow automatically replacing a defective robot with an optimal alternatively available robot. Finally, a remote interface, which could be run through the Cloud, allows users to manipulate fleets of robots from anywhere and to obtain access to sensors’ data. A practical scenario using five different robots has been realized to demonstrate the different possibilities. This demonstrates the cost effectiveness of our middleware in terms of its impacts on the communication network. Finally, a simulation study that evaluates the scalability of our middleware clearly shows that TalkRoBots can be used efficiently in industrial scenarios involving a huge number of heterogeneous robots and IIoT devices.