In this paper we describe and compare multiple one-class anomaly detection methods for Cyber-Physical Systems (CPS) that can be trained with data collected only during normal behaviors. We also consider the problem of detecting which group of sensors is most affected by the anomalous situation solving an open-set classification task. The proposed methods are domain independent and are based on a temporal analysis of data collected by the system. More specifically, we use different flavours of deep learning architectures, including recurrent neural networks (RNN), temporal convolutional networks (TCN), and autoencoders. Experimental results are conducted in three different scenarios with publicly available datasets: social robots, autonomous boats and water treatment plants (SWaT dataset). Quantitative results on these datasets show that our approach achieves comparable results with respect to state of the art approaches and promising results for open-set classification.
Exploiting Time Dynamics for One-Class and Open-Set Anomaly Detection / Brigato, L.; Sartea, R.; Simonazzi, S.; Farinelli, A.; Iocchi, L.; Napoli, C.. - 12855:(2021), pp. 137-148. (Intervento presentato al convegno 20th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2021 tenutosi a Zakopane, Poland) [10.1007/978-3-030-87897-9_13].
Exploiting Time Dynamics for One-Class and Open-Set Anomaly Detection
Brigato L.Co-primo
Investigation
;Simonazzi S.Co-primo
;Iocchi L.Penultimo
Supervision
;Napoli C.
Ultimo
Supervision
2021
Abstract
In this paper we describe and compare multiple one-class anomaly detection methods for Cyber-Physical Systems (CPS) that can be trained with data collected only during normal behaviors. We also consider the problem of detecting which group of sensors is most affected by the anomalous situation solving an open-set classification task. The proposed methods are domain independent and are based on a temporal analysis of data collected by the system. More specifically, we use different flavours of deep learning architectures, including recurrent neural networks (RNN), temporal convolutional networks (TCN), and autoencoders. Experimental results are conducted in three different scenarios with publicly available datasets: social robots, autonomous boats and water treatment plants (SWaT dataset). Quantitative results on these datasets show that our approach achieves comparable results with respect to state of the art approaches and promising results for open-set classification.File | Dimensione | Formato | |
---|---|---|---|
Brigato_postprint_Exploting-Time_2021.pdf.pdf
accesso aperto
Tipologia:
Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza:
Creative commons
Dimensione
282.8 kB
Formato
Adobe PDF
|
282.8 kB | Adobe PDF | |
Brigato_Exploting-Time_2021.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
512.15 kB
Formato
Adobe PDF
|
512.15 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.