2020/07/17 by Simon D. Duque Antón, Hans D. Schotten, Anton, Simon D Duque +1
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Fault Detection and Control Systems #Network Security and Intrusion Detection
paper · pdf · doi:10.48550/arxiv.2007.08813
openalex publication_date 2020/07/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The digitisation of industry provides a plethora of novel applications that\nincrease flexibility and reduce setup and maintenance time as well as cost.\nFurthermore, novel use cases are created by the digitisation of industry,\ncommonly known as Industry 4.0 or the Industrial Internet of Things,\napplications make use of communication and computation technology that is\nbecoming available. This enables novel business use cases, such as the digital\ntwin, customer individual production, and data market places. However, the\ninter-connectivity such use cases rely on also significantly increases the\nattack surface of industrial enterprises. Sabotage and espionage are aimed at\ndata, which is becoming the most crucial asset of an enterprise. Since the\nrequirements on security solutions in industrial networks are inherently\ndifferent from office networks, novel approaches for intrusion detection need\nto be developed. In this work, process data of a real water treatment process\nthat contains attacks is analysed. Analysis is performed by an extension of\nMatrix Profiles, a motif discovery algorithm for time series. By extending\nMatrix Profiles with a Hammingdistance metric, binary and tertiary actuators\ncan be integrated into the analysis in a meaningful fashion. This algorithm\nrequires low training effort while providing accurate results. Furthermore, it\ncan be employed in a real-time fashion. Selected actuators in the data set are\nanalysed to highlight the applicability of the extended Matrix Profiles.\n