Formal verification of neural networks?

Martin Leucker*

*Corresponding author for this work


Machine learning is a popular tool for building state of the art software systems. It is more and more used also in safety critical areas. This demands for verification techniques ensuring the safety and security of machine learning based solutions. However, we argue that the popularity of machine learning comes from the fact that no formal specification exists which renders traditional verification inappropriate. Instead, validation is typically demanded, but formalization of so far informal requirements is necessary to give formal evidence that the right system is build. Moreover, we present a recent technique that allows to check certain properties for an underlying recurrent neural network and which may be uses as a tool to identify whether the system learned is right.

Original languageEnglish
Title of host publicationSBMF 2020: Formal Methods: Foundations and Applications
EditorsGustavo Carvalho, Volker Stolz
Number of pages5
Volume12475 LNCS
PublisherSpringer, Cham
Publication date19.11.2020
ISBN (Print)978-3-030-63881-8
ISBN (Electronic)978-3-030-63882-5
Publication statusPublished - 19.11.2020
Event23rd Brazilian Symposium on Formal Methods - Ouro Preto, Brazil
Duration: 25.11.202027.11.2020
Conference number: 252049


Dive into the research topics of 'Formal verification of neural networks?'. Together they form a unique fingerprint.

Cite this