Testing-based Black-box Extraction of Simple Models from RNNs and Transformers

Edi Muskardin; Martin Tappler; Bernhard K. Aichernig

Testing-based Black-box Extraction of Simple Models from RNNs and Transformers

Edi Muskardin, Martin Tappler, Bernhard K. Aichernig

Trustworthy & Adaptive Computing (TAC)

Publikation: Konferenzband/Beitrag in Buch/Bericht › Konferenzartikel › Begutachtung

Abstract

In this technical report, we outline the testing-based black-box method used to extract simple and interpretable models from RNNs and transformers. Our work was done in the scope of the TAYSIR competition, in which it won the first place.

Originalsprache	Englisch
Titel	International Conference on Grammar Inference
Band	217
Publikationsstatus	Veröffentlicht - Juli 2023

Zugriff auf Dokument

https://proceedings.mlr.press/v217/muskardin23a/muskardin23a.pdf

Dieses zitieren

@inproceedings{6df480096d4d4ed1b8f58c9588129661,

title = "Testing-based Black-box Extraction of Simple Models from RNNs and Transformers",

abstract = "In this technical report, we outline the testing-based black-box method used to extract simple and interpretable models from RNNs and transformers. Our work was done in the scope of the TAYSIR competition, in which it won the first place.",

keywords = "Automata Learning, Model extraction, RNN, Transformers",

author = "Edi Muskardin and Martin Tappler and Aichernig, {Bernhard K.}",

year = "2023",

month = jul,

language = "English",

volume = "217",

booktitle = "International Conference on Grammar Inference",

}

TY - GEN

T1 - Testing-based Black-box Extraction of Simple Models from RNNs and Transformers

AU - Muskardin, Edi

AU - Tappler, Martin

AU - Aichernig, Bernhard K.

PY - 2023/7

Y1 - 2023/7

N2 - In this technical report, we outline the testing-based black-box method used to extract simple and interpretable models from RNNs and transformers. Our work was done in the scope of the TAYSIR competition, in which it won the first place.

AB - In this technical report, we outline the testing-based black-box method used to extract simple and interpretable models from RNNs and transformers. Our work was done in the scope of the TAYSIR competition, in which it won the first place.

KW - Automata Learning

KW - Model extraction

KW - RNN

KW - Transformers

M3 - Conference Paper

VL - 217

BT - International Conference on Grammar Inference

ER -

Testing-based Black-box Extraction of Simple Models from RNNs and Transformers

Abstract

Zugriff auf Dokument

Fingerprint

Dieses zitieren