Shared Certificates for Neural Network Verification

DOI10.1007/978-3-031-13185-1_7MaRDI QIDQ6487315zbMATH OpenFDO

Authors Marc Fischer, Gagandeep Singh, Martin Vechev

Publication date 7 December 2022

Copyright license Creative Commons Attribution 4.0 International

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Specification and verification (program logics, model checking, etc.) (68Q60)

Recommendations

• Branch and bound for piecewise linear neural network verification
• Scalable polyhedral verification of recurrent neural networks
• Formal verification of piece-wise linear feed-forward neural networks
• Exploiting verified neural networks via floating point numerical error
• Advances in verification of ReLU neural networks

Cites work

• A zonotopic framework for functional abstractions
• Grammar Analysis and Parsing by Abstract Interpretation
• Reluplex: an efficient SMT solver for verifying deep neural networks
• SAT-Based Model Checking without Unrolling

Cited in

(7)

• Brief Announcement
• Scalable polyhedral verification of recurrent neural networks
• T4V: exploring neural network architectures that improve the scalability of neural network verification
• Robustness Verification for Classifier Ensembles
• Verifying Neural Networks Against Backdoor Attacks
• \textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks
• Exploiting verified neural networks via floating point numerical error

This page was built for publication: Shared Certificates for Neural Network Verification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6487315)