A weight-wise watermarking technique for DNN models and its robustness against overwriting attack

Han He; Seok Kang; Yuji Sakamoto

doi:10.1117/12.2590783

13 March 2021 A weight-wise watermarking technique for DNN models and its robustness against overwriting attack

Han He, Seok Kang, Yuji Sakamoto

Proceedings Volume 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021; 1176627 (2021) https://doi.org/10.1117/12.2590783
Event: International Workshop on Advanced Imaging Technology 2021 (IWAIT 2021), 2021, Online Only

Abstract

With the increasing accuracy of Deep Neural Network (DNN) models, a high-performance DNN model becomes more and more expensive to train. Moreover, like common multimedia resources, DNN models will be distributed or shared over the Internet. For these reasons, a high-performance model can be considered as an Intellectual Property (IP). However, because of the nature of deep learning, conventional watermarks for DNN models are usually vulnerable to attack. To protect the authentication of these DNN models, we proposed a watermarking technique that performs satisfactorily in terms of security, robustness, and embedding capacity without impairing the accuracy of the host DNN model. However, it has not been compared with other techniques in terms of robustness against overwriting attack. To this end, we extend our previous work5 by conducting more comparison experiments to evaluate the performance of our method.

Citation Download Citation

Han He, Seok Kang, and Yuji Sakamoto "A weight-wise watermarking technique for DNN models and its robustness against overwriting attack", Proc. SPIE 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021, 1176627 (13 March 2021); https://doi.org/10.1117/12.2590783

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