Survey of Copyright Protection Schemes Based on DNN Model

被引：0
|
作者：
Fan X. [1 ]
Zhou X. [1 ]
Zhu B. [1 ]
Dong J. [2 ]
Niu J. [3 ]
Wang H. [2 ]
机构：
[1] School of Cyberspace Security, Hainan University, Haikou
[2] School of Cyber Engineering, Xidian University, Xi'an
[3] School of Computer Science and Technology, Xidian University, Xi'an
来源：
Jisuanji Yanjiu yu Fazhan/Computer Research and Development | 2022年 / 59卷 / 05期
关键词：
Black box watermarking; Copyright protection; Deep neural network (DNN); Gray box watermarking; Null box watermarking; White box watermarking;
D O I：
10.7544/issn1000-1239.20211115
中图分类号：
学科分类号：
摘要：
Emerging technologies such as the deep neural network (DNN) have been rapidly developed and applied in industrial Internet security with unprecedented performance. However, training a DNN model needs to capture a large number of proprietary data in different scenarios in the target application, to require extensive computing resources, and to adjust the network topology with the assistance of experts to properly train the parameters. As valuable intellectual property, DNN model should be technically protected from illegal reproduction, redistribution or abuse. Inspired by the classical watermarking technologies which protect intellectual property rights related to multimedia content, neural network watermarking is currently the DNN model copyright protection method most concerned by researchers. So far, there is no complete description of the application of neural network watermarking in the protection of intellectual property of DNN models. We investigate the relevant work of CCF recommended journals and conferences in recent five years. From the perspective of watermark embedding and extraction, based on the original classification of white box and black box watermarking, the neural network watermarking is extended to gray box and null box. The white box and black box watermarkings are summarized in details according to their different ideas and various task models, and the performances of the four classifications are compared. Finally, we discuss the future challenges and research directions of neural network watermarking, aiming to provide guidance to further promote such technologies for DNN model copyright protection. © 2022, Science Press. All right reserved.
引用
收藏
页码：953 / 977
页数：24
相关论文
共 116 条
  • [81] Fan Lixin, Ng W K, Chan C S., Rethinking deep neural network ownership verification: Embedding passports to defeat ambiguity attacks, Proc of the 33rd Conf on Neural Information Processing Systems, pp. 1-10, (2019)
  • [82] Zhang Jie, Chen Dongdong, Liao Jing, Et al., Passport-aware normalization for deep model protection, Advances in Neural Information Processing Systems, 33, pp. 22619-22628, (2020)
  • [83] Lu Peizhuo, Li Pan, Zhang Shengzhi, Et al., HufuNet: Embedding the left piece as watermark and keeping the right piece for ownership verification in deep neural networks
  • [84] Adi Y, Baum C, Cisse M, Et al., Turning your weakness into a strength: Watermarking deep neural networks by backdooring, Proc of the 27th USENIX Security, pp. 1615-1631, (2018)
  • [85] Namba R, Sakuma J., Robust watermarking of neural network with exponential weighting, Proc of the 2019 ACM Asia Conf on Computer and Communications Security, pp. 228-240, (2019)
  • [86] Merrer E L, Perez P, Tredan G., Adversarial frontier stitching for remote neural network watermarking, Neural Computing and Applications, 32, 13, pp. 9233-9244, (2020)
  • [87] Zhang Jialong, Gu Zhongshu, Jang Jiyong, Et al., Protecting intellectual property of deep neural networks with watermarking, Proc of the 2018 on Asia Conf on Computer and Communications Security, pp. 159-172, (2018)
  • [88] Guo Jia, Potkonjak M., Watermarking deep neural networks for embedded systems, Proc of the 2018 IEEE/ACM Int Conf on Computer-Aided Design, pp. 1-8, (2018)
  • [89] Li Zheng, Hu Chengyu, Zhang Yang, Et al., How to prove your model belongs to you: A blind-watermark based framework to protect intellectual property of DNN, Proc of the 35th Annual Computer Security Applications Conf, pp. 126-137, (2019)
  • [90] Zhong Qi, Zhang Leo Yu, Zhang Jun, Et al., Protecting IP of deep neural networks with watermarking: A new label helps, Advances in Knowledge Discovery and Data Mining, 12085, pp. 462-474, (2020)
3456789101112