Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper).

DOI10.4230/LIPICS.CONCUR.2019.1MaRDI QIDQ5875362zbMATH OpenOpenAlexFDO

Authors Marta Kwiatkowska

Publication date 3 February 2023

Full work available at URL https://drops.dagstuhl.de/opus/volltexte/2019/10903/pdf/LIPIcs-CONCUR-2019-1.pdf/

zbMATH Keywords

Bayesian neural networksformal verificationneural networksrobustness

Mathematics Subject Classification ID

Models and methods for concurrent and distributed computing (process algebras, bisimulation, transition nets, etc.) (68Q85)

Cites work

• A game-based approximate verification of deep neural networks with provable guarantees
• An empirical study of QBF encodings: from treewidth estimation to useful preprocessing
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Safety verification of deep neural networks

Cited in

(3)

• Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
• Theorem Proving in Higher Order Logics
• Learning safe neural network controllers with barrier certificates

Describes a project that uses

Uses Software

• SIFT

This page was built for publication: Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper).

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5875362)