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

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks

Artificial Intelligence 2024-05-21 v2 Machine Learning Logic in Computer Science

Authors: 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

View on arXiv ↗ PDF ↗

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.

Keywords

neural network verification formal analysis Marabou framework satisfiability modulo theories abstract interpretation deep learning

Cite

@article{arxiv.2401.14461,
  title  = {Marabou 2.0: A Versatile Formal Analyzer of Neural Networks},
  author = {Haoze Wu and Omri Isac and Aleksandar Zeljić and Teruhiro Tagomori and Matthew Daggitt and Wen Kokke and Idan Refaeli and Guy Amir and Kyle Julian and Shahaf Bassan and Pei Huang and Ori Lahav and Min Wu and Min Zhang and Ekaterina Komendantskaya and Guy Katz and Clark Barrett},
  journal= {arXiv preprint arXiv:2401.14461},
  year   = {2024}
}

Comments

Condensed version accepted at CAV'24

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks

Abstract

Keywords

Cite

Comments

Related papers