Verisig 2.0: verification of neural network controllers using Taylor model preconditioning

DOI10.1007/978-3-030-81685-8_11MaRDI QIDQ832173zbMATH OpenOpenAlexFDO

Authors Radoslav Ivanov, Taylor Carpenter, James Weimer, Rajeev Alur, Insup Lee, George Pappas

Publication date 25 March 2022

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/978-3-030-81685-8_11

Mathematics Subject Classification ID

Nonlinear ordinary differential equations and systems (34A34) General methods in interval analysis (65G40) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by ordinary differential equations (93C15) Numerical methods for initial value problems involving ordinary differential equations (65L05)

Recommendations

• Verisig
• Formal verification of neural network controlled autonomous systems
• An abstraction-based framework for neural network verification
• Formal verification of piece-wise linear feed-forward neural networks
• Branch and bound for piecewise linear neural network verification
• Advances in verification of ReLU neural networks
• A learner-verifier framework for neural network controllers and certificates of stochastic systems

Cites work

• Case study
• Formal verification of neural network controlled autonomous systems
• Formal verification of piece-wise linear feed-forward neural networks
• Gray-box adversarial testing for control systems with machine learning components
• On Taylor Model Based Integration of ODEs
• Reachability analysis for neural feedback systems using regressive polynomial rule inference
• Reluplex: an efficient SMT solver for verifying deep neural networks
• S-TaLiRo: a tool for temporal logic falsification for hybrid systems
• Safety verification of deep neural networks
• Suppression of the wrapping effect by Taylor model-based verified integrators: long-term stabilization by preconditioning
• The algorithmic analysis of hybrid systems
• Verification of deep convolutional neural networks using ImageStars
• Verisig

Cited in

(8)

• Verified propagation of imprecise probabilities in non-linear ODEs
• A framework for the competitive analysis of model predictive controllers
• Automatic Abstraction Refinement in Neural Network Verification using Sensitivity Analysis
• Generating probabilistic safety guarantees for neural network controllers
• Verisig
• RINO: Robust INner and Outer Approximated Reachability of Neural Networks Controlled Systems
• T4V: exploring neural network architectures that improve the scalability of neural network verification
• Reachability analysis of a general class of neural ordinary differential equations

Describes a project that uses

Uses Software

• Scenic
• ReachNN
• AI2
• Reluplex
• Breach
• Flow*
• SpaceEx
• S-TaLiRo

This page was built for publication: Verisig 2.0: verification of neural network controllers using Taylor model preconditioning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q832173)