Learning Finite State Models fromRecurrent Neural Networks

Edi Muškardin*, Bernhard K. Aichernig, Ingo Pill, Martin Tappler

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung


Explaining and verifying the behavior of recurrent neural networks (RNNs) is an important step towards achieving confidence in machine learning. The extraction of finite state models, like deterministic automata, has been shown to be a promising concept for analyzing RNNs. In this paper, we apply a black-box approach based on active automata learning combined with model-guided conformance testing to learn finite state machines (FSMs) from RNNs. The technique efficiently infers a formal model of an RNN classifier’s input-output behavior, regardless of its inner structure. In several experiments, we compare this approach to other state-of-the-art FSM extraction methods. By detecting imprecise generalizations in RNNs that other techniques miss, model-guided conformance testing learns FSMs that more accurately model the RNNs under examination. We demonstrate this by identifying counterexamples with this testing approach that falsifies wrong hypothesis models learned by other techniques. This entails that testing guided by learned automata can be a useful method for finding adversarial inputs, that is, inputs incorrectly classified due to improper generalization.

TitelIntegrated Formal Methods - 17th International Conference, IFM 2022, Proceedings
Redakteure/-innenMaurice H. ter Beek, Rosemary Monahan
Herausgeber (Verlag)Springer Science and Business Media Deutschland GmbH
ISBN (elektronisch)978-3-031-07727-2
ISBN (Print)9783031077265
PublikationsstatusVeröffentlicht - 2022
Veranstaltung17th International Conference on Integrated Formal Methods: IFM 2022 - Lugano, Schweiz
Dauer: 7 Juni 202210 Juni 2022


NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (elektronisch)1611-3349


Konferenz17th International Conference on Integrated Formal Methods

ASJC Scopus subject areas

  • Theoretische Informatik
  • Informatik (insg.)


Untersuchen Sie die Forschungsthemen von „Learning Finite State Models fromRecurrent Neural Networks“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren