The hexatope and octatope abstract domains for neural network verification

DOI10.1007/s10703-024-00457-yMaRDI QIDQ6661753

Taylor Dohmen, Alvaro Velasquez, K. Subramani and Vahan Mkrtchyan, Ashutosh Trivedi, Piotr J. Wojciechowski, Stanley Bak

Publication date: 13 January 2025

Published in: Formal Methods in System Design (Search for Journal in Brave)

zbMATH Keywords

zonotopesstar setsabstract domainsdifference constraint systemneural network verificationunit-two-variables-per-inequality (UTVPI) constaint system

Mathematics Subject Classification ID

Computer science (68-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Robustness verification of semantic segmentation neural networks using relaxed reachability
• The octagon abstract domain
• A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Verification of deep convolutional neural networks using ImageStars
• Improved geometric path enumeration for verifying ReLU neural networks
• Finding minimum-cost circulations by canceling negative cycles
• Parsimonious, Simulation Based Verification of Linear Systems
• Solving Linear Programs in the Current Matrix Multiplication Time
• Subexponential lower bounds for randomized pivoting rules for the simplex algorithm
• Frontiers of Combining Systems
• The octatope abstract domain for verification of neural networks
• Star-based reachability analysis of deep neural networks

This page was built for publication: The hexatope and octatope abstract domains for neural network verification