Demo: The Neural Network Verification (NNV) Tool

Hoang Dung Tran, Diego Manzanas Lopez, Xiaodong Yang, Patrick Musau, Luan Viet Nguyen, Weiming Xiang, Stanley Bak, Taylor T. Johnson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

NNV (Neural Network Verification) is a framework for the verification of deep neural networks (DNNs) and learning-enabled cyber-physical systems (CPS) inspired by a collection of reachability algorithms that make use of a variety of set representations such as the star set. NNV supports exact and over-approximate reachability algorithms used to verify the safety and robustness of feed-forward neural networks (FFNNs). These two analysis schemes are also used for learning enabled CPS, i.e., closed-loop systems, and particularly in neural network control systems with linear models and FFNN controllers with piecewise-linear activation functions. Additionally, NNV supports over-approximate analysis for nonlinear plant models by combining the star set analysis used for FFNNs with the zonotope-based analysis for nonlinear plant dynamics provided by CORA. This demo paper demonstrates NNV's capabilities by considering a case study of the verification of a learning-enabled adaptive cruise control system.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE Workshop on Design Automation for CPS and IoT, DESTION 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages21-22
Number of pages2
ISBN (Electronic)9781728199948
DOIs
StatePublished - Apr 2020
Event2020 IEEE Workshop on Design Automation for CPS and IoT, DESTION 2020 - Sydney, Australia
Duration: Apr 21 2020 → …

Publication series

NameProceedings - 2020 IEEE Workshop on Design Automation for CPS and IoT, DESTION 2020

Conference

Conference2020 IEEE Workshop on Design Automation for CPS and IoT, DESTION 2020
CountryAustralia
CitySydney
Period4/21/20 → …

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Automotive Engineering
  • Control and Optimization

Fingerprint Dive into the research topics of 'Demo: The Neural Network Verification (NNV) Tool'. Together they form a unique fingerprint.

Cite this