An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks

Zhi Qin Tan, Hao Shan Wong, Chee Seng Chan


Abstract
Capitalise on deep learning models, offering Natural Language Processing (NLP) solutions as a part of the Machine Learning as a Service (MLaaS) has generated handsome revenues. At the same time, it is known that the creation of these lucrative deep models is non-trivial. Therefore, protecting these inventions’ intellectual property rights (IPR) from being abused, stolen and plagiarized is vital. This paper proposes a practical approach for the IPR protection on recurrent neural networks (RNN) without all the bells and whistles of existing IPR solutions. Particularly, we introduce the Gatekeeper concept that resembles the recurrent nature in RNN architecture to embed keys. Also, we design the model training scheme in a way such that the protected RNN model will retain its original performance iff a genuine key is presented. Extensive experiments showed that our protection scheme is robust and effective against ambiguity and removal attacks in both white-box and black-box protection schemes on different RNN variants. Code is available at https://github.com/zhiqin1998/RecurrentIPR.
Anthology ID:
2022.aacl-main.8
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
93–105
Language:
URL:
https://aclanthology.org/2022.aacl-main.8
DOI:
Bibkey:
Cite (ACL):
Zhi Qin Tan, Hao Shan Wong, and Chee Seng Chan. 2022. An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 93–105, Online only. Association for Computational Linguistics.
Cite (Informal):
An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks (Tan et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.aacl-main.8.pdf