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

TL;DR

DAICS is a deep learning framework designed for anomaly detection in industrial control systems that adapts to evolving system behaviors, reducing false alarms and maintaining high detection accuracy without human intervention.

Contribution

The paper introduces DAICS, a modular deep learning approach with a 2-branch neural network and automatic threshold tuning for effective anomaly detection in dynamic ICS environments.

Findings

Higher detection rate and accuracy compared to existing methods

Increased robustness to additive noise

Effective adaptation to system behavior changes with minimal data

Abstract

Deep Learning is emerging as an effective technique to detect sophisticated cyber-attacks targeting Industrial Control Systems (ICSs). The conventional approach to detection in literature is to learn the "normal" behaviour of the system, to be then able to label noteworthy deviations from it as anomalies. However, during operations, ICSs inevitably and continuously evolve their behaviour, due to e.g., replacement of devices, workflow modifications, or other reasons. 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.