An abstraction-based framework for neural network verification

DOI10.1007/978-3-030-53288-8_3zbMath1478.68154arXiv1910.14574OpenAlexW3102139284MaRDI QIDQ2225075

Guy Katz, Justin Gottschlich, Yizhak Yisrael Elboher

Publication date: 4 February 2021

Full work available at URL: https://arxiv.org/abs/1910.14574

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Specification and verification (program logics, model checking, etc.) (68Q60)

Related Items (14)

Robustness verification of quantum classifiers ⋮ \textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks ⋮ Property-directed verification and robustness certification of recurrent neural networks ⋮ Bisimulations for neural network reduction ⋮ Metrics and methods for robustness evaluation of neural networks with generative models ⋮ Reluplex: a calculus for reasoning about deep neural networks ⋮ \textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks ⋮ Neural Network Verification Using Residual Reasoning ⋮ Reachability analysis of deep ReLU neural networks using facet-vertex incidence ⋮ SMT-based modeling and verification of spiking neural networks: a case study ⋮ Boosting robustness verification of semantic feature neighborhoods ⋮ An SMT-based approach for verifying binarized neural networks ⋮ Improving neural network verification through spurious region guided refinement ⋮ Enhancing robustness verification for deep neural networks via symbolic propagation

This page was built for publication: An abstraction-based framework for neural network verification