Cyber-Resilient Digital Twins: Discriminating Attacks for Safe Critical Infrastructure Control

2026-03-19

AI Summary

Industrial cyber-physical systems are vulnerable to cyberattacks targeting sensors and control components, yet existing digital twin approaches struggle to accurately distinguish between attack types and often rely on costly full-system shutdowns. To address this, this work proposes i-SDT, an intelligent self-defensive digital twin framework that, for the first time, enables precise discrimination between single-stage and multi-stage attacks within a digital twin architecture. The framework integrates hydraulic regularization-based predictive modeling, a maximum mean discrepancy–driven recurrent residual encoder, and an uncertainty-aware model predictive controller to achieve adaptive, resilient responses without system interruption. Evaluated on the SWaT and WADI datasets, the method significantly improves detection accuracy, reduces false alarm rates by 44.1%, lowers operational costs by 56.3%, and achieves inference latency under one second, meeting real-time deployment requirements.

Technology Category

• Intelligent Robots: State Estimation
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Industrial Cyber-Physical Systems (ICPS) face growing threats from cyber-attacks that exploit sensor and control vulnerabilities. Digital Twin (DT) technology can detect anomalies via predictive modelling, but current methods cannot distinguish attack types and often rely on costly full-system shutdowns. This paper presents i-SDT (intelligent Self-Defending DT), combining hydraulically-regularized predictive modelling, multi-class attack discrimination, and adaptive resilient control. Temporal Convolutional Networks (TCNs) with differentiable conservation constraints capture nominal dynamics and improve robustness to adversarial manipulations. A recurrent residual encoder with Maximum Mean Discrepancy (MMD) separates normal operation from single- and multi-stage attacks in latent space. When attacks are confirmed, Model Predictive Control (MPC) uses uncertainty-aware DT predictions to keep operations safe without shutdown. Evaluation on SWaT and WADI datasets shows major gains in detection accuracy, 44.1% fewer false alarms, and 56.3% lower operational costs in simulation-in-the-loop evaluation. with sub-second inference latency confirming real-time feasibility on plant-level workstations, i-SDT advances autonomous cyber-physical defense while maintaining operational resilience.

Problem

• Cyber-attacks
• Digital Twin
• Industrial Cyber-Physical Systems
• Attack Discrimination
• Critical Infrastructure

Innovation

• Digital Twin
• Attack Discrimination
• Temporal Convolutional Network
• Model Predictive Control
• Cyber-Physical Security