Watermarking Neural Networks With Watermarked Images

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 7; pp. 2591 - 2601
• Main Authors: Wu, Hanzhou, Liu, Gen, Yao, Yuwei, Zhang, Xinpeng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.07.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; deep learning; Digital imaging; Digital watermarking; Image processing; Image resolution; Image segmentation; image transformation; information hiding; Intellectual property; IP networks; Media; Neural networks; Task analysis; Training; Watermarking
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2020.3030671

Watermarking neural networks is a quite important means to protect the intellectual property (IP) of neural networks. In this paper, we introduce a novel digital watermarking framework suitable for deep neural networks that output images as the results, in which any image outputted from a watermarked neural network must contain a certain watermark. Here, the host neural network to be protected and a watermark-extraction network are trained together, so that, by optimizing a combined loss function, the trained neural network can accomplish the original task while embedding a watermark into the outputted images. This work is totally different from previous schemes carrying a watermark by network weights or classification labels of the trigger set. By detecting watermarks in the outputted images, this technique can be adopted to identify the ownership of the host network and find whether an image is generated from a certain neural network or not. We demonstrate that this technique is effective and robust on a variety of image processing tasks, including image colorization, super-resolution, image editing, semantic segmentation and so on.