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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Tianhao, Hu, Hanjiang, Marzari, Luca, Yun, Kai S., Niu, Peizhi, Luo, Xusheng, Liu, Changliu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908456281178112
author Wei, Tianhao
Hu, Hanjiang
Marzari, Luca
Yun, Kai S.
Niu, Peizhi
Luo, Xusheng
Liu, Changliu
author_facet Wei, Tianhao
Hu, Hanjiang
Marzari, Luca
Yun, Kai S.
Niu, Peizhi
Luo, Xusheng
Liu, Changliu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_01639
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks
Wei, Tianhao
Hu, Hanjiang
Marzari, Luca
Yun, Kai S.
Niu, Peizhi
Luo, Xusheng
Liu, Changliu
Machine Learning
Software Engineering
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.
title ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks
topic Machine Learning
Software Engineering
url https://arxiv.org/abs/2407.01639