abstract
- Industry 4.0 is built upon the foundation of connecting devices and systems via Internet of Things (IoT) technologies, with Cyber-Physical Systems (CPS) serving as the backbone infrastructure. Although this approach brings numerous benefits like improved performance, responsiveness and reconfigurability, it also introduces security concerns, making devices and systems vulnerable to cyber attacks. There is a need for effective techniques to protect these systems, and the availability of datasets becomes essential to support the development of such techniques. This paper presents a dataset based on the collection of traffic information exchanged in a self-organizing conveyor system using the multi-agent systems (MAS) architecture and containing various intelligent conveyor modules. The dataset comprises data collected at the network and agent levels under normal system operation, denial of service (DoS) attacks, and malicious agent attacks. An intrusion detection system that integrates Fast Fourier Transform (FFT) and Machine Learning (ML) analysis is developed to demonstrate the utility of this dataset.
- The authors are grateful to the Foundation for Science and Technology (FCT, Portugal) for financial support through national funds FCT/MCTES (PIDDAC) to CeDRI (UIDB/05757/2020 and UIDP/05757/2020) and SusTEC (LA/P/0007/2021). The authors Gustavo Funchal and Vict´oria Melo thank the FCT for the PhD Grants 2022.13712.BD and 2022.13868.BD.