Improving neural network verification through spurious region guided refinement

DOI10.1007/978-3-030-72016-2_21zbMath1467.68096arXiv2010.07722OpenAlexW3147451797MaRDI QIDQ2044215

Yanyan Li

Publication date: 4 August 2021

Full work available at URL: https://arxiv.org/abs/2010.07722

Mathematics Subject Classification ID

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

Related Items (3)

\textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks ⋮ \textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks ⋮ Improving neural network verification through spurious region guided refinement

Cites Work

• Unnamed Item
• Unnamed Item
• The contraction principle as a particular case of Kleene's fixed point theorem
• Improving neural network verification through spurious region guided refinement
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Verification of deep convolutional neural networks using ImageStars
• An abstraction-based framework for neural network verification
• A game-based approximate verification of deep neural networks with provable guarantees
• CVXPY: A Python-Embedded Modeling Language for Convex Optimization
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Fast polyhedra abstract domain

This page was built for publication: Improving neural network verification through spurious region guided refinement