Weight grouping method for generation management of watermarks for white-box DNN models

Ryu Furukawa; Shigeyuki Sakazawa

doi:10.1117/12.3018256

2 May 2024 Weight grouping method for generation management of watermarks for white-box DNN models

Ryu Furukawa, Shigeyuki Sakazawa

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 131640Z (2024) https://doi.org/10.1117/12.3018256
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

DNN models have become increasingly popular in recent years, and developers' rights need to be protected due to the various costs involved in creating DNN models. In this context, research on embedding watermarks to assert the copyright of DNN models has attracted attention. Furthermore, it is well known that secondary use of DNN models can be used to create high-performance models specialized for specific tasks, and that secondary use is readily available. In the case of legitimate secondary use, it is necessary to protect the rights of both the original model developer and the derived model developer. To achieve copyright protection of DNN models over multiple generations, this study proposes a method for embedding multiple watermarks. When multiple watermarks are embedded sequentially, there is a concern about interference between watermarks. The proposed method avoids this problem by grouping the DNN weight parameters used for watermarking. The proposed grouping also makes it possible to represent more information as watermark than in our previous study. Furthermore, embedding the watermark using the proposed method has a small impact on the original task.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ryu Furukawa and Shigeyuki Sakazawa "Weight grouping method for generation management of watermarks for white-box DNN models", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 131640Z (2 May 2024); https://doi.org/10.1117/12.3018256

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available