First three years of the international verification of neural networks competition (VNN-COMP)

This paper presents a summary and meta-analysis of the first three iterations of the annual International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021, and 2022. In the VNN-COMP, participants submit software tools that analyze whether given neural networks satisfy speci...

Full description

Saved in:
Bibliographic Details
Published in:International journal on software tools for technology transfer Vol. 25; no. 3; pp. 329 - 339
Main Authors: Brix, Christopher, Müller, Mark Niklas, Bak, Stanley, Johnson, Taylor T., Liu, Changliu
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2023
Springer Nature B.V
Subjects:
Aircraft
Benchmarks
Classification
Competition
Computer Science
Deep learning
Explanation Paradigms Leveraging Analytic Intuition
Image classification
Machine learning
Neural networks
Software
Software Engineering
Software Engineering/Programming and Operating Systems
Software utilities
Specifications
Theory of Computation
Trends
Verification
Deep learning
Adversarial robustness
Neural networks
Certified robustness
Machine learning
Formal methods
Formal verification
ISSN:1433-2779, 1433-2787
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a summary and meta-analysis of the first three iterations of the annual International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021, and 2022. In the VNN-COMP, participants submit software tools that analyze whether given neural networks satisfy specifications describing their input-output behavior. These neural networks and specifications cover a variety of problem classes and tasks, corresponding to safety and robustness properties in image classification, neural control, reinforcement learning, and autonomous systems. We summarize the key processes, rules, and results, present trends observed over the last three years, and provide an outlook into possible future developments.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1433-2779
1433-2787
DOI:10.1007/s10009-023-00703-4