On neural network equivalence checking using SMT solvers

DOI10.1007/978-3-031-15839-1_14OpenAlexW4293399511MaRDI QIDQ2112128

Stavros Tripakis, Panagiotis Katsaros, Charis Eleftheriadis, Nikolaos Kekatos

Publication date: 18 January 2023

Full work available at URL: https://arxiv.org/abs/2203.11629

zbMATH Keywords

verificationneural networkequivalence checkingSMT

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Uses Software

• ImageNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Hierarchical multi-label classification using local neural networks
• A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
• Reluplex: an efficient SMT solver for verifying deep neural networks
• An SMT-based approach for verifying binarized neural networks
• Decision procedures. An algorithmic point of view. With foreword by Randal E. Bryant