Property-Directed Verification of Recurrent Neural Networks

This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a given RNN using active automata learning. This model may then be analyzed using model checking as verification technique....

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-09
Main Authors: Khmelnitsky, Igor, Neider, Daniel, Roy, Rajarshi, Barbot, Benoît, Bollig, Benedikt, Finkel, Alain, Haddad, Serge, Leucker, Martin, Ye, Lina
Format: Article
Language:English
Subjects:
Neural networks
Recurrent neural networks
Verification
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a given RNN using active automata learning. This model may then be analyzed using model checking as verification technique. The term property-directed reflects the idea that our procedure is guided and controlled by the given property rather than performing the two steps separately. We show that this not only allows us to discover small counterexamples fast, but also to generalize them by pumping towards faulty flows hinting at the underlying error in the RNN.
ISSN:2331-8422