DPR-GM (Domain-Prior-Regularized Graph Modeling), a forecasting-based framework that incorporates system design knowledge into graph construction, is proposed, showing that domain-structured graph priors are a practical alternative to fully learned topologies in data-scarce CPS.
Abstract
Anomaly detection on multivariate sensor time series is critical for industrial monitoring of cyber-physical systems (CPS), where even subtle deviations from normal behavior can indicate process disruption. Recent graph-based approaches have made significant progress, but they often struggle in small-scale physical systems with scarce labeled anomalies and limited normal data. In such settings, graph-based models tend to capture spurious correlations and produce unstable sensor topologies. We propose DPR-GM (Domain-Prior-Regularized Graph Modeling), a forecasting-based framework that incorporates system design knowledge into graph construction. DPR-GM leverages a large language model (LLM) to extract directed physical couplings between sensor pairs from system documentation, which are encoded as a binary domain adjacency matrix serving as a structural gate over sensor relations. This gate is then modulated by Pearson correlations estimated from normal training data. The anomaly score is further weighted by sensor-level reliability derived from the coefficient of variation. All graph and weighting components are fixed prior to training and add no learnable parameters. On the SKAB benchmark, DPR-GM outperforms graph-based, statistical, and deep learning baselines across F1, AUROC, and AUPRC, showing that domain-structured graph priors are a practical alternative to fully learned topologies in data-scarce CPS.
NS-MFM-DGA is introduced, a neural-symbolic multimodal foundation model that incorporates dynamic graph attention for real-time anomaly detection in SD-ICPS and provides a feasible and explainable low-latency anomaly-detection framework for supervisory monitoring in SD-ICPS.
Multivariate time series anomaly detection (MTAD) is important for ensuring reliable operation and improving service quality in industrial systems. Forecasting-based methods have been a primary approach for MTAD, detecting anomalies by assuming that anomalous data points produce higher forecasting errors than normal on...
W. Koo, Heeyoung Kim· IISE Annual Conference &...· 0 citations
An explainable GNN-based anomaly detection framework is proposed that shifts the perspective from sensor-level anomalies to component-level diagnosis, hypothesizing that anomalous measurements are symptoms of altered inter-sensor influences.
Sena Ozgunay, Louise Travé-Massuyès, Jean-Michel Loubes et al.· 0 citations
Unsupervised multivariate time series anomaly detection methods typically identify anomalies through forecasting, reconstruction, or representation discrepancies. However, industrial faults may first alter inter-variable structural patterns while individual trajectories remain close to normal, resulting in weak anomaly...
Ze-Peng Zhang, F. Khūrī, Keivan Faghih Niresi et al.· 1 citation
A graph-based anomaly detection model tailored for power generation systems using multivariate time-series data that incorporates both spatial and temporal dependencies is presented, demonstrating the advantages of incorporating both spatial and temporal dependencies.
Dongwook Kwon, Youngshin Kang, Jiwoon Lee et al.· Data mining and knowledge di...· 0 citations
Cyber-physical systems (CPSs) consist of sensors, controllers, and actuators through communication and physical interactions, making them vulnerable to attacks on measurements, control logic, and equipment operation. Graph-based attack detectors, especially graph attention models, can localize such attacks by learning...
Zhenan Feng, Ehsan Nekouei· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.