The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Alberti, Michele, Bobot, François, Girard-Satabin, Julien, Grastien, Alban, Varasse, Aymeric, Chihani, Zakaria
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917210651361280
author Alberti, Michele
Bobot, François
Girard-Satabin, Julien
Grastien, Alban
Varasse, Aymeric
Chihani, Zakaria
author_facet Alberti, Michele
Bobot, François
Girard-Satabin, Julien
Grastien, Alban
Varasse, Aymeric
Chihani, Zakaria
contents The formal specification and verification of machine learning programs saw remarkable progress in less than a decade, leading to a profusion of tools. However, diversity may lead to fragmentation, resulting in tools that are difficult to compare, except for very specific benchmarks. Furthermore, this progress is heavily geared towards the specification and verification of a certain class of property, that is, local robustness properties. But while provers are becoming more and more efficient at solving local robustness properties, even slightly more complex properties, involving multiple neural networks for example, cannot be expressed in the input languages of winners of the International Competition of Verification of Neural Networks VNN-Comp. In this tool paper, we present CAISAR, an open-source platform dedicated to machine learning specification and verification. We present its specification language, suitable for modelling complex properties on neural networks, support vector machines and boosted trees. We show on concrete use-cases how specifications written in this language are automatically translated to queries to state-of-the-art provers, notably by using automated graph editing techniques, making it possible to use their off-the-shelf versions. The artifact to reproduce the paper claims is available at the following DOI: https://doi.org/10.5281/zenodo.15209510
format Preprint
id arxiv_https___arxiv_org_abs_2506_12084
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification
Alberti, Michele
Bobot, François
Girard-Satabin, Julien
Grastien, Alban
Varasse, Aymeric
Chihani, Zakaria
Software Engineering
Artificial Intelligence
Computation and Language
Formal Languages and Automata Theory
Neural and Evolutionary Computing
The formal specification and verification of machine learning programs saw remarkable progress in less than a decade, leading to a profusion of tools. However, diversity may lead to fragmentation, resulting in tools that are difficult to compare, except for very specific benchmarks. Furthermore, this progress is heavily geared towards the specification and verification of a certain class of property, that is, local robustness properties. But while provers are becoming more and more efficient at solving local robustness properties, even slightly more complex properties, involving multiple neural networks for example, cannot be expressed in the input languages of winners of the International Competition of Verification of Neural Networks VNN-Comp. In this tool paper, we present CAISAR, an open-source platform dedicated to machine learning specification and verification. We present its specification language, suitable for modelling complex properties on neural networks, support vector machines and boosted trees. We show on concrete use-cases how specifications written in this language are automatically translated to queries to state-of-the-art provers, notably by using automated graph editing techniques, making it possible to use their off-the-shelf versions. The artifact to reproduce the paper claims is available at the following DOI: https://doi.org/10.5281/zenodo.15209510
title The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification
topic Software Engineering
Artificial Intelligence
Computation and Language
Formal Languages and Automata Theory
Neural and Evolutionary Computing
url https://arxiv.org/abs/2506.12084