Predictive Monitoring of Black-Box Dynamical Systems

Thomas A. Henzinger, Fabian Kresse, Kaushik Mallik, Emily Yu, \DJor\dje Žikelić
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:804-816, 2025.

Abstract

We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and that we are only able to observe the state of the controlled (aka, closed-loop) system at finitely many time points. We present a novel framework for predicting future states of the system based on the states observed in the past. The numbers of past states and of predicted future states are parameters provided by the user. Our method is based on a combination of Taylor’s expansion and the backward difference operator for numerical differentiation. We also derive an upper bound on the prediction error under the assumption that the system dynamics and the controller are smooth. The predicted states are then used to predict safety violations ahead in time. Our experiments demonstrate practical applicability of our method for complex black-box systems, showing that it is computationally lightweight and yet significantly more accurate than the state-of-the-art predictive safety monitoring techniques.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-henzinger25a, title = {Predictive Monitoring of Black-Box Dynamical Systems}, author = {Henzinger, Thomas A. and Kresse, Fabian and Mallik, Kaushik and Yu, Emily and \v{Z}ikeli\'{c}, \DJ{}or\dj{}e}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {804--816}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/henzinger25a/henzinger25a.pdf}, url = {https://proceedings.mlr.press/v283/henzinger25a.html}, abstract = {We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and that we are only able to observe the state of the controlled (aka, closed-loop) system at finitely many time points. We present a novel framework for predicting future states of the system based on the states observed in the past. The numbers of past states and of predicted future states are parameters provided by the user. Our method is based on a combination of Taylor’s expansion and the backward difference operator for numerical differentiation. We also derive an upper bound on the prediction error under the assumption that the system dynamics and the controller are smooth. The predicted states are then used to predict safety violations ahead in time. Our experiments demonstrate practical applicability of our method for complex black-box systems, showing that it is computationally lightweight and yet significantly more accurate than the state-of-the-art predictive safety monitoring techniques.} }
Endnote
%0 Conference Paper %T Predictive Monitoring of Black-Box Dynamical Systems %A Thomas A. Henzinger %A Fabian Kresse %A Kaushik Mallik %A Emily Yu %A \DJor\dje Žikelić %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-henzinger25a %I PMLR %P 804--816 %U https://proceedings.mlr.press/v283/henzinger25a.html %V 283 %X We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and that we are only able to observe the state of the controlled (aka, closed-loop) system at finitely many time points. We present a novel framework for predicting future states of the system based on the states observed in the past. The numbers of past states and of predicted future states are parameters provided by the user. Our method is based on a combination of Taylor’s expansion and the backward difference operator for numerical differentiation. We also derive an upper bound on the prediction error under the assumption that the system dynamics and the controller are smooth. The predicted states are then used to predict safety violations ahead in time. Our experiments demonstrate practical applicability of our method for complex black-box systems, showing that it is computationally lightweight and yet significantly more accurate than the state-of-the-art predictive safety monitoring techniques.
APA
Henzinger, T.A., Kresse, F., Mallik, K., Yu, E. & Žikelić, \.. (2025). Predictive Monitoring of Black-Box Dynamical Systems. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:804-816 Available from https://proceedings.mlr.press/v283/henzinger25a.html.

Related Material