Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack

02/08/2021 ∙ by Ding Sheng Ong, et al. ∙ 15

Ever since Machine Learning as a Service (MLaaS) emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties. To the best of our knowledge, one of the prominent deep learning models - Generative Adversarial Networks (GANs) which has been widely used to create photorealistic image are totally unprotected despite the existence of pioneering IPR protection methodology for Convolutional Neural Networks (CNNs). This paper therefore presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs. Empirically, we show that the proposed method does not compromise the original GANs performance (i.e. image generation, image super-resolution, style transfer), and at the same time, it is able to withstand both removal and ambiguity attacks against embedded watermarks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

page 7

page 11

page 12

page 13

page 14

page 15

page 16

Code Repositories

ipr-gan

This is the code repo of our CVPR2021 on protecting the IPR of Generative Adversarial Networks (GANs) from Ambiguity Attack


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.