Formal analysis of neural network-based systems in the aircraft domain
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Neural networks are being increasingly used for efficient decision making in the aircraft domain. Given the safety-critical nature of the applications involved, stringent safety requirements must be met by these networks. In this work we present a formal study of two neural network-based systems developed by Boeing. The Venus verifier is used to analyse the conditions under which these systems can operate safely, or generate counterexamples that show when safety cannot be guaranteed. Our results confirm the applicability of formal verification to the settings considered.
Date Issued
2021-11-10
Date Acceptance
2021-11-01
Citation
2021, pp.730-740
ISBN
9783030908690
ISSN
0302-9743
Publisher
Springer International Publishing
Start Page
730
End Page
740
Copyright Statement
© Springer Nature Switzerland AG 2021.
The final publication is available at Springer via https://doi.org/10.1007/978-3-030-90870-6_41
The final publication is available at Springer via https://doi.org/10.1007/978-3-030-90870-6_41
Sponsor
Defence Advanced Research Projects Agency (UK)
Royal Academy Of Engineering
Identifier
https://link.springer.com/chapter/10.1007%2F978-3-030-90870-6_41
Grant Number
Ref: FA8750-18-C-0095
CIET\TUA\2021\12
Source
International Symposium on Formal Methods
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2021-11-20
Finish Date
2021-11-26
Coverage Spatial
Beijing, China
Date Publish Online
2021-11-10