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

TL;DR

The CAISAR platform provides a unified, extensible environment for specifying and verifying complex properties of machine learning models, supporting multiple model types and leveraging existing provers through automated translation.

Contribution

It introduces a novel specification language and an open-source platform that enable modeling and verification of complex ML properties across various model types.

Findings

Supports complex properties involving multiple models

Automates translation to existing provers

Demonstrates effectiveness on real-world use cases

Abstract

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