arXiv:2603.10676v2 Announce Type: replace Abstract: Industrial Control Systems (ICS) underpin critical infrastructure and face growing cyber-physical threats due to the convergence of operational technology and networked environments. While machine learning-based anomaly detection approaches in ICS shows strong theoretical performance, deployment is often limited by poor explainability, high false-positive rates, and sensitivity to evolving system behavior, i.e., baseline drifting. We propose a Spatio-Temporal Attention Graph Neural Network (STA-GNN) for unsupervised and explainable anomaly de
The increasing integration of operational technology with networked environments makes critical infrastructure highly vulnerable, creating an urgent need for explainable and robust anomaly detection methods.
Explainability and robustness in AI for critical infrastructure, particularly in industrial control systems, are crucial for national security and economic stability given the growing cyber-physical threats.
The development of explainable AI models like STA-GNN can improve the deployment and efficacy of machine learning-based anomaly detection in sensitive environments by reducing false positives and improving trust.
- · Industrial Control System operators
- · Cybersecurity firms
- · Critical infrastructure sectors
- · AI/ML explainability researchers
- · Malicious cyber actors
- · Legacy anomaly detection systems
Improved reliability and security of critical infrastructure through better anomaly detection.
Increased adoption of AI and machine learning in operational technology environments due to enhanced trust and explainability.
Potential for new regulations and standards mandating explainable AI for systems governing critical infrastructure.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG