Cyber-Physical Behaviour Detection and Understanding using Artificial Intelligence

Abstract

The advancement of cyber-physical behaviour detection and understanding in context of urban environment safety and security has been developed in the S4AllCities project (S4AllCities, 2020). Specifically, various concepts of fundamental artificial intelligence and reasoning have been successfully developed and will subsequently be tested in situ in S4AllCities pilot sites during the coming year 2022 (Sabeur et al, 2021). The detection of anomalies in TCP and UDP communication-based protocols taking place in context of urban spaces have been investigated. These were also complemented with the detection of unusualness in crowd physical behaviour in the same urban spaces. The aim is to combine both modes (cyber and physical) of detection and behaviour understanding, in order to advance our situation awareness in context of native knowledge and reasoning for efficiently maintaining safety and security across the urban space. Native knowledge concerns the evaluated risks and mitigation measures for response to potential cyber-physical attacks on the urban space. In this study, the deployed machine learning techniques achieved good performances for classifying cyber and physical behaviour under various scenarios of potential attacks. Our future work is to exercise the performance, evaluation and validation of our intelligent algorithms using in situ cyber and physical observation scenarios of the urban spaces of the three S4AllCities pilot sites in Europe.References:S4AllCities (2020). Safe and Secure Smart Spaces for all Cities H2020 project ID number 883522. https://www.s4allcities.eu/project. Sabeur Z., Angelopoulos C.M., Collick L., Chechina N., Cetinkaya D., Bruno A. (2021) Advanced Cyber and Physical Situation Awareness in Urban Smart Spaces. In: Ayaz H., Asgher U., Paletta L. (eds) Advances in Neuroergonomics and Cognitive Engineering. AHFE 2021. Lecture Notes in Networks and Systems, vol 259. pp. 428-441. Springer, Cham. https://doi.org/10.1007/978-3-030-80285-1_50