Advances in verification of ReLU neural networks

DOI10.1007/S10898-020-00949-1zbMATH Open1478.68172OpenAlexW3033072407MaRDI QIDQ2046329FDOQ2046329

Ansgar Rössig, Milena R. Petkovic

Publication date: 17 August 2021

Published in: Journal of Global Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10898-020-00949-1

zbMATH Keywords

MIPReLUneural networks verification

Mathematics Subject Classification ID

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

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Three enhancements for optimization-based bound tightening
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Deep neural networks and mixed integer linear optimization
• Strong mixed-integer programming formulations for trained neural networks
• Challenging SMT solvers to verify neural networks

Cited In (6)

• Robustness verification of semantic segmentation neural networks using relaxed reachability
• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning
• Reluplex: an efficient SMT solver for verifying deep neural networks
• An abstraction-based framework for neural network verification
• Improved geometric path enumeration for verifying ReLU neural networks
• Challenging SMT solvers to verify neural networks

Uses Software

• SCIP
• Reluplex
• AI2
• RecurJac

This page was built for publication: Advances in verification of ReLU neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2046329)