Quantitative Verification for Neural Networks using ProbStars

DOI10.1145/3575870.3587112MaRDI QIDQ6202079zbMATH OpenOpenAlexFDO

Authors Hoang-Dung Tran, Sung Woo Choi, Bardh Hoxha, Georgios E. Fainekos, Danil Prokhorov

Publication date 21 February 2024

Published in Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1145/3575870.3587112

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)

Cites work

• Computation of multivariate normal and \(t\) probabilities
• Improved geometric path enumeration for verifying ReLU neural networks
• Neural network repair with reachability analysis
• Numerical computation of multivariate normal probabilities using bivariate conditioning
• Numerical verification of affine systems with up to a billion dimensions
• Parsimonious, Simulation Based Verification of Linear Systems
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Rigorous simulation-based analysis of linear hybrid systems
• Robustness verification of semantic segmentation neural networks using relaxed reachability
• Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
• Sherlock - A tool for verification of neural network feedback systems
• Simulation-equivalent reachability of large linear systems with inputs
• Statistical verification of learning-based cyber-physical systems
• The normal law under linear restrictions: simulation and estimation via minimax tilting
• Verification of deep convolutional neural networks using ImageStars
• Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter
• Verifying binarized neural networks by Angluin-style learning
• Verifying low-dimensional input neural networks via input quantization
• \textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks

This page was built for publication: Quantitative Verification for Neural Networks using ProbStars

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6202079)