MADICS: A Methodology for Anomaly Detection in Industrial Control Systems

Abstract

Industrial Control Systems (ICSs) are widely used in critical infrastructures to support the essential services of society. Therefore, their protection against terrorist activities, natural disasters, and cyber threats is critical. Diverse cyber attack detection systems have been proposed over the years, in which each proposal has applied different steps and methods. However, there is a significant gap in the literature regarding methodologies to detect cyber attacks in ICS scenarios. The lack of such methodologies prevents researchers from being able to accurately compare proposals and results. In this work, we present a Methodology for Anomaly Detection in Industrial Control Systems (MADICS) to detect cyber attacks in ICS scenarios, which is intended to provide a guideline for future works in the field. MADICS is based on a semi-supervised anomaly detection paradigm and makes use of deep learning algorithms to model ICS behaviors. It consists of five main steps, focused on pre-processing the dataset to be used with the machine learning and deep learning algorithms; performing feature filtering to remove those features that do not meet the requirements; feature extraction processes to obtain higher order features; selecting, fine-tuning, and training the most appropriate model; and validating the model performance. In order to validate MADICS, we used the popular Secure Water Treatment (SWaT) dataset, which was collected from a fully operational water treatment plant. The experiments demonstrate that, using MADICS, we can achieve a state-of-the-art precision of 0.984 (as well as a recall of 0.750 and F1-score of 0.851), which is above the average of other works, proving that the proposed methodology is suitable for use in real ICS scenarios.

SafeMan: A unified framework to manage cybersecurity and safety in manufacturing industry

“…In this work, we used an open industrial dataset named Electra, 45,46 which contains protocols like the ones we found on our scenario. Specifically, Electra includes four S7Comm devices and three Modbus TCP devices.…”

Light-weight federated learning-based anomaly detection for time-series data in industrial control systems

“…Being inherently sequential hinders parallelization within samples, which slows down training and inference processes, especially with long sequences. Therefore, work [15], [16], [17], and [18], for example, did not yield significant anomaly detection performance when employing LSTM and GRU for ICS time series data. In work [15], the author presented a data-driven predictive modeling approach for ICS systems.…”

A TOPSIS-Assisted Feature Selection Scheme and SOM-Based Anomaly Detection for Milling Tools Under Different Operating Conditions

“…The different anomaly detection approaches are evaluated on the basis of the following performance indicators: accu-racy [45], anomaly detection rate (recall) [34], false alarm rate [34], and F1-score [45] which are expressed in ( 22)- (25), respectively. The precision indicator that is needed for calculating F1-score is expressed in (26) [45].…”