First three years of the international verification of neural networks competition (VNN-COMP)
Open access
Date
2023-06Type
- Journal Article
Abstract
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000617162Publication status
publishedExternal links
Journal / series
International Journal on Software Tools for Technology TransferVolume
Pages / Article No.
Publisher
SpringerSubject
Certified robustness; Adversarial robustness; Formal verification; Formal methods; Neural networks; Machine learning; Deep learningMore
Show all metadata