Marabou 2.0: A Versatile Formal Analyzer of Neural Networks

Haoze Wu*, Omri Isac, Aleksandar Zeljić, Teruhiro Tagomori, Matthew Daggitt, Wen Kokke, Idan Refaeli, Guy Amir, Kyle Julian, Shahaf Bassan, Pei Huang, Ori Lahav, Min Wu, Min Zhang, Ekaterina Komendantskaya, Guy Katz, Clark Barrett

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Downloads (Pure)

Abstract

This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool’s architectural design and highlight the major features and components introduced since its initial release.

Original languageEnglish
Title of host publicationComputer Aided Verification. CAV 2024
EditorsArie Gurfinkel, Vijay Ganesh
PublisherSpringer
Pages249-264
Number of pages16
ISBN (Electronic)9783031656309
ISBN (Print)9783031656293
DOIs
Publication statusPublished - 25 Jul 2024
Event36th International Conference on Computer Aided Verification 2024 - Montreal, Canada
Duration: 24 Jul 202427 Jul 2024

Publication series

NameLecture Notes in Computer Science
Volume14682
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference36th International Conference on Computer Aided Verification 2024
Abbreviated titleCAV 2024
Country/TerritoryCanada
CityMontreal
Period24/07/2427/07/24

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Marabou 2.0: A Versatile Formal Analyzer of Neural Networks'. Together they form a unique fingerprint.

Cite this