ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks

TL;DR

ModelVerification.jl is a comprehensive toolbox that integrates multiple state-of-the-art methods for verifying various properties of deep neural networks, enhancing trustworthiness and safety in AI applications.

Contribution

It introduces the first all-in-one toolbox for verifying diverse DNN properties, combining multiple verification techniques in a single framework.

Findings

Provides a versatile suite of verification tools for DNNs.

Enables verification of different safety specifications.

Supports diverse DNN architectures.

Abstract

Deep Neural Networks (DNN) are crucial in approximating nonlinear functions across diverse applications, ranging from image classification to control. Verifying specific input-output properties can be a highly challenging task due to the lack of a single, self-contained framework that allows a complete range of verification types. To this end, we present \texttt{ModelVerification.jl (MV)}, the first comprehensive, cutting-edge toolbox that contains a suite of state-of-the-art methods for verifying different types of DNNs and safety specifications. This versatile toolbox is designed to empower developers and machine learning practitioners with robust tools for verifying and ensuring the trustworthiness of their DNN models.