Quantitative Verification for Neural Networks using ProbStars
DOI10.1145/3575870.3587112OpenAlexW4375852012MaRDI QIDQ6202079
Sung Woo Choi, Hoang-Dung Tran, Unnamed Author, 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
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
- \textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks
- Robustness verification of semantic segmentation neural networks using relaxed reachability
- Computation of multivariate normal and \(t\) probabilities
- Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter
- Neural network repair with reachability analysis
- Verifying low-dimensional input neural networks via input quantization
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Simulation-equivalent reachability of large linear systems with inputs
- Verifying binarized neural networks by Angluin-style learning
- Verification of deep convolutional neural networks using ImageStars
- Improved geometric path enumeration for verifying ReLU neural networks
- Numerical Computation of Multivariate Normal Probabilities Using Bivariate Conditioning
- Rigorous Simulation-Based Analysis of Linear Hybrid Systems
- Parsimonious, Simulation Based Verification of Linear Systems
- Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
- Statistical verification of learning-based cyber-physical systems
- Numerical verification of affine systems with up to a billion dimensions
- Sherlock - A tool for verification of neural network feedback systems
- The Normal Law Under Linear Restrictions: Simulation and Estimation via Minimax Tilting
This page was built for publication: Quantitative Verification for Neural Networks using ProbStars
