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.
翻译:自机器学习服务(MLaaS)成为利用深层次学习模式创造盈利收入的可行行业以来,知识产权(IPR)已成为一个主要关切,因为这些深层次学习模式很容易被任何未经授权的第三方复制、共享和再分配。 据我们所知,一个著名的深层次学习模式 — — 创世反向网络(GANs)被广泛用来创造光现实形象,尽管存在革命神经网络(CNNs)的先驱性知识产权保护方法,但却完全得不到保护。 因此,本文在黑箱和白箱设置中提供了一个完整的保护框架,对GANs实施知识产权保护。 我们生动地表明,拟议方法不会损害原GANs的性能(即图像生成、图像超分辨率、风格转换 ), 同时,它能够承受对嵌入水印的去除和模糊攻击。