PhaseNet++ introduces a novel frequency-domain autoencoder for anomaly detection in Industrial Control Systems (ICS), addressing the overlooked phase spectrum in multivariate time series analysis. It utilizes a Phase Coherence Index to guide a graph attention network for enhanced detection of cyber-physical attacks.
This paper introduces a high-fidelity, physics-informed co-simulation of an aircraft main-fuel-pump system to generate data for anomaly detection and diagnosis algorithms. It addresses the inherent lack of data in critical cyber-physical systems and demonstrates feasibility using unsupervised RNN-VAE and SOM-VAE models.
Industry 4.0 requires robust anomaly detection in Cyber-Physical Systems (CPS), but product-agnostic models have blind spots for subtle anomalies or targeted attacks. This work demonstrates this vulnerability and proposes a Product-Aware Autoencoder as a mitigation by restricting the learning domain.