Digital Twin-based Anomaly Detection in Cyber-physical Systems

Abstract

Cyber-Physical Systems (CPS) are susceptible to various anomalies during their operations. Thus, it is important to detect such anomalies. Detecting such anomalies is challenging since it is uncertain when and where anomalies can happen. To this end, we present a novel approach called Anomaly deTection with digiTAl twIN (ATTAIN), which continuously and automatically builds a digital twin with live data obtained from a CPS for anomaly detection. ATTAIN builds a Timed Automaton Machine (TAM) as the digital representation of the CPS, and implements a Generative Adversarial Network (GAN) to detect anomalies. GAN uses a GCN-LSTM-based module as a generator, which can capture temporal and spatial characteristics of the input data and learn to produce realistic unlabeled adversarial samples. TAM labels these adversarial samples, which are then fed into a discriminator along with real labeled samples. After training, the discriminator is capable of distinguishing anomalous data from normal data with a high F1 score. To evaluate our approach, we used three publicly available datasets collected from three CPS testbeds. Evaluation results show that ATTAIN improved the performance of two state-of-art anomaly detection methods by 2.413%, 8.487%, and 5.438% on average on the three datasets, respectively. Moreover, ATTAIN achieved on average 8.39% increase in the anomaly detection capability with digital twins as compared with an approach of not using digital twins.

Design, Modeling and Implementation of Digital Twins

“…The approach also proposes secure estimation against stealthy estimation attacks and control for CPS using a game theory mechanism. Xu et al [ 36 ] also present aDT for anomaly detection, but they proposal continuously and automatically building theDT with live data from a CPS. This creates a Generative Adversarial Network (GAN) to capture the temporal and spatial characteristics of the input data and recognize adversarial samples.…”

Digital twin-enabled automated anomaly detection and bottleneck identification in complex manufacturing systems using a multi-agent approach

“…Akin to the two previously discussed works, the actual model developed by Xu et al [59] is a digital shadow as only unidirectional communication between the physical and virtual entities is enabled [10]. Recently, Q. Xu et al [60] proposed an Anomaly deTection with DT (ATTAIN) approach to detect anomalies in CPSs. The proposed approach enables the continuous and automated construction of the DT using real-time data acquired from a CPS.…”

A Subspace Method for Time Series Anomaly Detection in Cyber-Physical Systems

“…Remark 4. Even though, the estimates obtained in this section provide specific criteria to identify possible regions for anomaly localization or behavioral changes, for discrete time signals data that have been measured from some given dynamical system, dealing with real sensor signals corresponding to cyber-physical systems can be very challenging as observed by Xu et al (2021), and may require some heuristic tuning of the parameters and meta-parameters involved in the computational process corresponding to anomaly detection algorithms. This fact has been taken into account for the computational implementation of the ideas presented in this section.…”

“…We will also work on more adaptive and artificially intelligent schemes that combine linear and nonlinear models, along the lines of Vides (2021a), where the linear part of the models can be computed using the methods discussed in this document. Applications to digital twins simulation, aimed to provide alternative solution strategies to the problems identified in Xu et al (2021), will also be studied and discussed in future communications.…”