Gray-box adversarial testing for control systems with machine learning components

DOI10.1145/3302504.3311814MaRDI QIDQ5239235zbMATH OpenOpenAlexFDO

Authors Shakiba Yaghoubi, Georgios E. Fainekos

Publication date 22 October 2019

Published in Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1812.11958

zbMATH Keywords

optimizationneural networktesting and verification

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)

Recommendations

• Learning safe neural network controllers with barrier certificates
• Verifying Neural Network Controlled Systems Using Neural Networks
• Learning safe neural network controllers with barrier certificates
• Stability Analysis for State Feedback Control Systems Established as Neural Networks with Input Constraints
• Verisig

Cited in

(3)

• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning
• A framework based on symbolic regression coupled with eXtended physics-informed neural networks for gray-box learning of equations of motion from data
• Compositional falsification of cyber-physical systems with machine learning components

This page was built for publication: Gray-box adversarial testing for control systems with machine learning components

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5239235)