Back to articles
Volume: 32 | Article ID: art00003
Watermarking in Deep Neural Networks via Error Back-propagation
  DOI :  10.2352/ISSN.2470-1173.2020.4.MWSF-022  Published OnlineJanuary 2020

Recent advances in deep learning (DL) have led to great success in tasks of computer vision and pattern recognition. Sharing pre-trained DL models has been an important means to promote the rapid progress of research community and development of DL based systems. However, it also raises challenges to model authentication. It is quite necessary to protect the ownership of the DL models to be released. In this paper, we present a digital watermarking technique to deep neural networks (DNNs). We propose to mark a DNN by inserting an independent neural network that allows us to use selective weights for watermarking. The independent neural network is only used in the training phase and watermark verification phase, and will not be released publicly. Experiments have shown that, the performance of marked DNN on its original task will not be degraded significantly. Meantime, the watermark can be successfully embedded and extracted with a low neural network loss even under the common attacks including model fine-tuning and compression, which has shown the superiority and applicability of the proposed work.

Subject Areas :
Views 113
Downloads 48
 articleview.views 113
 articleview.downloads 48
  Cite this article 

Jiangfeng Wang, Hanzhou Wu, Xinpeng Zhang, Yuwei Yao, "Watermarking in Deep Neural Networks via Error Back-propagationin Proc. IS&T Int’l. Symp. on Electronic Imaging: Media Watermarking, Security, and Forensics,  2020,  pp 22-1 - 22-9,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA