Parallelization Techniques for Verifying Neural Networks

Haoze Wu, Alex Ozdemir, Aleksandar Zeljic, Kyle Julian, Ahmed Irfan, Divya Gopinath, Sadjad Fouladi, Guy Katz, Corina Pasareanu, Clark Barrett

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

26 Scopus citations

Abstract

Inspired by recent successes of parallel techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics to leverage parallelism and improve the scalability of neural network verification. We present a general description of the Split-and-Conquer partitioning algorithm, implemented within the Marabou framework, and discuss its parameters and heuristic choices. In particular, we explore two novel partitioning strategies, that partition the input space or the phases of the neuron activations, respectively. We introduce a branching heuristic and a direction heuristic that are based on the notion of polarity. We also introduce a highly parallelizable pre-processing algorithm for simplifying neural network verification problems. An extensive experimental evaluation shows the benefit of these techniques on both existing and new benchmarks. A preliminary experiment ultra-scaling our algorithm using a large distributed cloud-based platform also shows promising results.

Original languageAmerican English
Title of host publicationProceedings of the 20th Conference on Formal Methods in Computer-Aided Design, FMCAD 2020
EditorsAlexander Ivrii, Ofer Strichman, Warren A. Hunt, Georg Weissenbacher
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages128-137
Number of pages10
ISBN (Electronic)9783854480426
DOIs
StatePublished - 21 Sep 2020
Event20th International Conference on Formal Methods in Computer-Aided Design, FMCAD 2020 - Virtual, Haifa, Israel
Duration: 21 Sep 202024 Sep 2020

Publication series

NameProceedings of the 20th Conference on Formal Methods in Computer-Aided Design, FMCAD 2020

Conference

Conference20th International Conference on Formal Methods in Computer-Aided Design, FMCAD 2020
Country/TerritoryIsrael
CityVirtual, Haifa
Period21/09/2024/09/20

Bibliographical note

Publisher Copyright:
© 2020 FMCAD Association.

Fingerprint

Dive into the research topics of 'Parallelization Techniques for Verifying Neural Networks'. Together they form a unique fingerprint.

Cite this