NeuralVerificaiton.jl: Algorithms for verifying deep neural networks - Robotics Institute Carnegie Mellon University

NeuralVerificaiton.jl: Algorithms for verifying deep neural networks

C. Liu, T. Arnon, C. Lazarus, and M. Kochenderfer
Workshop Paper, ICLR '19 Debugging Machine Learning Models Workshop, May, 2019

Abstract

Deep neural networks (DNNs) are widely used for nonlinear function approximation with applications ranging from computer vision to control. Although DNNs involve the composition of simple arithmetic operations, it can be very challenging to verify whether a particular network satisfies certain input-output properties.

This work introduces NeuralVerification.jl, a software package that implements
methods that have emerged recently for soundly verifying such properties. These
methods borrow insights from reachability analysis, optimization, and search. We
present the formal problem definition and briefly discuss the fundamental differences between the implemented algorithms. In addition, we provide a pedagogical example of how to use the library.

Notes
Best Applied Paper Award

BibTeX

@workshop{Liu-2019-119899,
author = {C. Liu and T. Arnon and C. Lazarus and M. Kochenderfer},
title = {NeuralVerificaiton.jl: Algorithms for verifying deep neural networks},
booktitle = {Proceedings of ICLR '19 Debugging Machine Learning Models Workshop},
year = {2019},
month = {May},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.