Method for copyright protection of deep neural networks using digital watermarking

Yuliya Vybornova

doi:10.1117/12.2623444

4 March 2022 Method for copyright protection of deep neural networks using digital watermarking

Yuliya Vybornova

Proceedings Volume 12084, Fourteenth International Conference on Machine Vision (ICMV 2021); 1208412 (2022) https://doi.org/10.1117/12.2623444
Event: Fourteenth International Conference on Machine Vision (ICMV 2021), 2021, Rome, Italy

Abstract

In this paper, a new method for protection of copyright on pretrained deep neural networks is proposed. The main idea is to embed a digital watermark into a pretrained model by finetuning the final layer weights. A deep neural network is retrained on a unique trigger set formed by synthesizing pseudo-holographic images and embedding them into raster images of the original dataset. In order to provide the accuracy of the original model, the deep model watermarking process is implemented with addition of a new class intended for the elements of the trigger sample. Experimental results show that the quality of the original model is not affected by watermarking process. Furthermore, the model can be retrained to distinguish the watermark of a legal owner from unauthorized one.

Citation Download Citation

Yuliya Vybornova "Method for copyright protection of deep neural networks using digital watermarking", Proc. SPIE 12084, Fourteenth International Conference on Machine Vision (ICMV 2021), 1208412 (4 March 2022); https://doi.org/10.1117/12.2623444

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