Digital twinML-assisted Bayesian Calibration of Accelerator Digital TwinarXiv API — полнотекстовый поиск "digital twin" · 14hDigital twinDigital Twin Testbed for Cyberattack and Defense Analysis in Hospital IT/OT EnvironmentsarXiv API — полнотекстовый поиск "digital twin" · 18hModellingGenerative Agent-based Simulation of Mobility Policy Preferences from SurveysarXiv — Computers and Society (cs.CY) · yesterdayForecastingScalable Gaussian Process with Trigonometric Features for Safe MPCarXiv — Systems and Control (eess.SY) · yesterdayForecastingTwo-Layer MPC for Sustainable Data Centers with Workload Flexibility and Heat RecoveryarXiv — Systems and Control (eess.SY) · yesterdayForecastingIterative MPC without Derivatives for Constrained Nonlinear SystemsarXiv — Systems and Control (eess.SY) · yesterdayForecastingDisturbance-adaptive MPC with Bounds on Average Constraint ViolationsarXiv — Systems and Control (eess.SY) · yesterdayDigital twinDigital Twin Degradation: Detecting Cyber Physical Attacks via Temporal InconsistenciesarXiv API — полнотекстовый поиск "digital twin" · yesterdayForecastingControl Architecture for Fast Frequency Regulation with High Inverter-Based Resource PenetrationarXiv — Systems and Control (eess.SY) · 2dDigital twinDigital Twin-Based Intrusion Detection for Vehicle Powertrain CAN BusarXiv API — полнотекстовый поиск "digital twin" · yesterdayDigital twinPRISM: Decision-Centric Predictive Sensing for Cognitive Digital Twins in 6GarXiv API — полнотекстовый поиск "digital twin" · yesterdayModellingNeural Network-Based Parameter Estimation for a Labour Market ABMarXiv — Multiagent Systems (cs.MA) · 2d
Digital Twin-Based Intrusion Detection for Vehicle Powertrain CAN Bus
US & West ·
A digital twin-based intrusion detection system is developed that models physical relationships among powertrain signals and identifies attacks via residuals. A shared-encoder LSTM was trained on real CAN data to predict seven numeric and two categorical signals.
Why it matters
The news addresses digital twins for cybersecurity in transportation, relevant for managing large fleets and infrastructure.
Original headline
Digital Twin-Based Intrusion Detection for Vehicle Powertrain CAN Bus Systems
The study parametrizes hard-to-measure effects and calibrates the Bmad accelerator digital twin using Bayesian methods with beam measurements at AGS Booster, BNL. Computations are accelerated with an ML emulator.
A testbed emulating hospital IT and OT infrastructure, including EHR and SCADA, with a digital twin for monitoring and experimentation, is presented. It supports controlled cyberattacks, patch evaluation, and training of defense agents, enabling safe testing of defensive mechanisms in realistic settings.
A method detects cyber-physical attacks by monitoring temporal inconsistencies between a physical system and its digital twin. A predictor trained on normal behavior generates multi-horizon features from residuals to flag anomalies.
