Skip to main navigation Skip to search Skip to main content

Protecting the Ownership of Deep Learning Models with An End-to-End Watermarking Framework

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep neural network (DNN), as a key component of deep learning technology, plays a vital role in its development. Most major technology companies use deep neural network as a key component to build their artificial intelligence products and service. Building a deep neural network model requires us to pay a huge price: large-scale labeled data sets, a large number of computing resources, and highly specialized domain knowledge. Therefore, we believe that the model owner owns the intellectual property rights of the model, and it is very important to design a technology that protects the intellectual property rights of the deep neural network model and allows the owner to externally verify its copyright. Through statistical analysis of a large number of pre-trained network parameters, we propose an end-to-end network model protection framework-Deep Water based on the distribution of network model parameters. First, we propose a new research problem: embedding watermarks into deep neural networks. We also define the requirements for watermarking in deep neural networks, the embedding situation, and the types of attacks. Secondly, we propose a general framework for embedding the watermark into the parameter distribution function of each layer of the convolutional network. Our method does not harm the performance of the network where the watermark is placed, because the watermark is embedded when the host network is trained. Finally, we conducted a comprehensive experiment to reveal the potential of watermarking deep neural networks as the basis for this new research work. We proved that our framework can embed watermarks in the process of training deep neural networks from scratch and in the process of fine-tuning and distillation without compromising its performance. Even after migration learning and watermark overlay operations, the embedded watermark will not disappear. Even if 65% of the parameters are trimmed, the watermark remains intact.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2021
EditorsLiang Zhao, Neeraj Kumar, Robert C. Hsu, Deqing Zou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages76-82
Number of pages7
ISBN (Electronic)9781665416580
DOIs
StatePublished - 2021
Event20th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2021 - Shenyang, China
Duration: 20 Oct 202122 Oct 2021

Publication series

NameProceedings - 2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2021

Conference

Conference20th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2021
Country/TerritoryChina
CityShenyang
Period20/10/2122/10/21

Keywords

  • Deep Neural Network
  • Intellectual property protection
  • Model parameters
  • Model stealing
  • Watermarking

Fingerprint

Dive into the research topics of 'Protecting the Ownership of Deep Learning Models with An End-to-End Watermarking Framework'. Together they form a unique fingerprint.

Cite this