Tolerance of CNN watermarking against model optimizations

Yudai Yamaji; Shigeyuki Sakazawa

doi:10.1117/12.2625769

30 April 2022 Tolerance of CNN watermarking against model optimizations

Yudai Yamaji, Shigeyuki Sakazawa

Proceedings Volume 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022; 121771R (2022) https://doi.org/10.1117/12.2625769
Event: International Workshop on Advanced Imaging Technology 2022 (IWAIT 2022), 2022, Hong Kong, China

Abstract

Models created by companies and individuals by training a large amount of data are important assets and need to be protected by copyright. As a method of copyright protection, experiments have been conducted to embed a watermark into the learning model. This watermark is embedded directly into the parameters of the learning model, but the values of the parameters will change when the learning model is subjected to model compression process such as quantization. In our previous study, we showed that the effect of quantization on the watermark was small and that the embedded watermark could be retrieved. In this paper, as a further investigation, we conduct experiments on the effect of both pruning and quantization, and quantization aware training on the watermarking when creating the trained model. In the experiments, we used models of two different scales, one large and one small, and performed the above-mentioned processing on each model to check the state of the watermark. The results show that the models with both pruning and quantization show significant degradation of the watermark for small-scale models, but this is eliminated when the models are quantized. In the case of quantization aware training, there was no effect on watermarking.

Citation Download Citation

Yudai Yamaji and Shigeyuki Sakazawa "Tolerance of CNN watermarking against model optimizations", Proc. SPIE 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022, 121771R (30 April 2022); https://doi.org/10.1117/12.2625769

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