Deep Learning is emerging as an effective technique to detect sophisticated cyber-attacks targeting Industrial Control Systems (ICSs). The conventional detection approach is to learn the normal behaviour of the system, to be then able to label noteworthy deviations from it as anomalies. However, the normal behaviour of ICSs continuously evolves over time for multiple reasons, such as update/replacement of devices, workflow modifications or others. As a consequence, the accuracy of the anomaly detection process may be dramatically affected with a considerable amount of false alarms being generated. This paper presents DAICS, a novel deep learning framework with a modular design to fit in large ICSs. The key component of the framework is a 2-branch neural network that learns the changes in the ICS behaviour with a small number of data samples and a few gradient updates. This is supported by an automatic tuning mechanism of the detection threshold that takes into account the changes in the prediction error under normal operating conditions. In this regard, no specialised human intervention is needed to update the other parameters of the system. DAICS has been evaluated using publicly available datasets and shows an increased detection rate and accuracy compared to state-of-the-art approaches, as well as higher robustness to additive noise.

DAICS: A Deep Learning Solution for Anomaly Detection in Industrial Control Systems

Abdelaty, Maged;Doriguzzi Corin, Roberto
Membro del Collaboration Group
;
Siracusa, Domenico
Membro del Collaboration Group
2022

Abstract

Deep Learning is emerging as an effective technique to detect sophisticated cyber-attacks targeting Industrial Control Systems (ICSs). The conventional detection approach is to learn the normal behaviour of the system, to be then able to label noteworthy deviations from it as anomalies. However, the normal behaviour of ICSs continuously evolves over time for multiple reasons, such as update/replacement of devices, workflow modifications or others. As a consequence, the accuracy of the anomaly detection process may be dramatically affected with a considerable amount of false alarms being generated. This paper presents DAICS, a novel deep learning framework with a modular design to fit in large ICSs. The key component of the framework is a 2-branch neural network that learns the changes in the ICS behaviour with a small number of data samples and a few gradient updates. This is supported by an automatic tuning mechanism of the detection threshold that takes into account the changes in the prediction error under normal operating conditions. In this regard, no specialised human intervention is needed to update the other parameters of the system. DAICS has been evaluated using publicly available datasets and shows an increased detection rate and accuracy compared to state-of-the-art approaches, as well as higher robustness to additive noise.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/326266
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact