PRIMA: general and precise neural network certification via scalable convex hull approximations

Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and relevant specifications remains an open and difficult challen...

Full description

Bibliographic Details

Published in:	Proceedings of ACM on programming languages Vol. 6; no. POPL; pp. 1 - 33
Main Authors:	Müller, Mark Niklas, Makarchuk, Gleb, Singh, Gagandeep, Püschel, Markus, Vechev, Martin
Format:	Journal Article
Language:	English
Published:	01.01.2022
ISSN:	2475-1421, 2475-1421
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!