T4V: exploring neural network architectures that improve the scalability of neural network verification

DOI10.1007/978-3-031-22337-2_28MaRDI QIDQ6113995zbMATH OpenFDO

Authors Vivian Lin, Radoslav Ivanov, James Weimer, Oleg Sokolsky, Insup Lee

Publication date 10 August 2023

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-031-22337-2_28

Mathematics Subject Classification ID

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

Recommendations

• An abstraction-based framework for neural network verification
• Exploiting verified neural networks via floating point numerical error
• Branch and bound for piecewise linear neural network verification
• Formal verification of piece-wise linear feed-forward neural networks
• Shared Certificates for Neural Network Verification

Cites work

• Case study
• Deep learning
• Formal verification of neural network controlled autonomous systems
• Formal verification of piece-wise linear feed-forward neural networks
• scientific article; zbMATH DE number 1507210 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Natural language processing (almost) from scratch
• Reachability analysis for neural feedback systems using regressive polynomial rule inference
• Reachability is NP-complete even for the simplest neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Verisig
• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning

Cited in

(3)

• \textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks
• Neural Network Verification Using Residual Reasoning
• Chordal sparsity for SDP-based neural network verification

This page was built for publication: T4V: exploring neural network architectures that improve the scalability of neural network verification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6113995)