CheckINN: Wide Range Neural Network Verification in Imandra

Remi Desmartin, Grant Passmore, Ekaterina Komendantskaya, Matthew Daggit

    Research output: Chapter in Book/Conference paperConference paperpeer-review

    Abstract

    Neural networks are increasingly relied upon as components of complex safety-critical systems such as autonomous vehicles. There is high demand for tools and methods that embed neural network verification in a larger verification cycle. However, neural network verification is difficult due to a wide range of verification properties of interest, each typically only amenable to verification in specialised solvers. In this paper, we show how Imandra, a functional programming language and a theorem prover originally designed for verification, validation and simulation of financial infrastructure can offer a holistic infrastructure for neural network verification. We develop a novel library CheckINN that formalises neural networks in Imandra, and covers different important facets of neural network verification.

    Original languageEnglish
    Title of host publicationProceedings of the 24th International Symposium on Principles and Practice of Declarative Programming, PPDP 2022 - Co-located with CLAS 2022 (including LOPSTR 2022)
    PublisherAssociation for Computing Machinery (ACM)
    ISBN (Electronic)9781450397032
    DOIs
    Publication statusPublished - 20 Sept 2022
    Event24th International Symposium on Principles and Practice of Declarative Programming, PPDP 2022 - Virtual, Online, Georgia
    Duration: 20 Sept 202222 Sept 2022

    Publication series

    NameACM International Conference Proceeding Series

    Conference

    Conference24th International Symposium on Principles and Practice of Declarative Programming, PPDP 2022
    Country/TerritoryGeorgia
    CityVirtual, Online
    Period20/09/2222/09/22

    Fingerprint

    Dive into the research topics of 'CheckINN: Wide Range Neural Network Verification in Imandra'. Together they form a unique fingerprint.

    Cite this