EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (19) · 21438-21445
DOI: 10.1609/aaai.v38i19.30140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xin Mu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper introduces a practical encryption-based framework called EncryIP, which seamlessly integrates a public-key encryption scheme into the model learning process. This approach enables the protected model to generate randomized and confused labels, ensuring that only individuals with accurate secret keys, signifying authorized users, can decrypt and reveal authentic labels. Importantly, the proposed framework not only facilitates the protected model to multiple authorized users without requiring repetitive training of the original ML model with IP protection methods but also maintains the model's performance without compromising its accuracy. Compared to existing methods like watermark-based, trigger-based, and passport-based approaches, EncryIP demonstrates superior effectiveness in both training protected models and efficiently detecting the unauthorized spread of ML models.
Zitieren
APA
Mu, X., Wang, Y., Huang, Z., Lai, J., Zhang, Y., Wang, H., & Yu, Y. (2024). EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(19), 21438-21445. https://doi.org/10.1609/aaai.v38i19.30140
Vancouver
Mu X, Wang Y, Huang Z, Lai J, Zhang Y, Wang H, et al. EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(19):21438-21445. doi:10.1609/aaai.v38i19.30140
BibTeX
@article{Mu2024,
author = {Mu, Xin and Wang, Yu and Huang, Zhengan and Lai, Junzuo and Zhang, Yehong and Wang, Hui and Yu, Yue},
title = {EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {19},
pages = {21438--21445},
doi = {10.1609/aaai.v38i19.30140}
}
EUVIMED