Interval universal approximation for neural networks
Abstract
To verify safety and robustness of neural networks, researchers have successfully applied abstract interpretation , primarily using the interval abstract domain. In this paper, we study the theoretical power and limits of the interval domain for neural-network verification.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jan 12, 2022
- Source ID
- 10.1145/3498675
Entities
People
- Aws Albarghouthi
- Gautam Prakriya
- Somesh Jha
- Zi Wang
Organizations
- Air Force Research Laboratory
- Army Research Office
- National Science Foundation
- The Chinese University of Hong Kong
- University of Wisconsin–Madison