ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

Watermark Removal Scheme Based on Neural Network Model Pruning

Gu, Wenwen*; Qian, Haifeng
5th International Conference on Machine Learning and Natural Language Processing (MLNLP)2022DOI: 10.1145/3578741.3578832
16阅读
引用收藏
分享

摘要

In recent years, due to the rapid development of information technology, machine learning is widely used in various fields. Training deep neural network models is a very expensive process, which requires a lot of training data and hardware resources. Therefore, DNN models can be considered the intellectual property rights of model owners and need to be protected. More and more watermarking algorithms have been studied to embed into neural network models to protect the ownership of the models. At the same time, to test the robustness of the watermark, watermarking attack algorithms have emerged. In this paper, we firstly find the unexpected sensitivity of watermarked models, that is, they are more susceptible to adversarial disturbances than unwatermarked models, and then propose a model repair method based on neural network model pruning. By pruning some sensitive neurons to remove the watermark, the success rate of the watermark can be reduced to a certain extent, and on this basis, it verifies that it can effectively avoid model ownership detection.

学科与关键词

关键词
Deep neural networkDigital watermarkingModel pruningWatermark removal
相关
加载中…
  • Watermarking Deep Neural Networks in Image Processing
    Quan, Yuhui; Teng, Huan; Chen, Yixin; Ji, Hui*IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(5): 1852-1865.被引 23
  • Deep Model Intellectual Property Protection via Deep Watermarking
    Zhang, Jie; Chen, Dongdong*; Liao, Jing; Zhang, Weiming; Feng, Huamin; Hua, Gang; Yu, NenghaiIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(8): 4005-4020.被引 38
  • NEURAL NETWORK FRAGILE WATERMARKING WITH NO MODEL PERFORMANCE DEGRADATION
    Yin, Zhaoxia*; Yin, Heng; Zhang, XinpengIEEE International Conference on Image Processing (ICIP), Bordeaux, FRANCE, 2022-10-16 To 2022-10-19.被引 4
查看全部 →

会议信息

会议名称
5th International Conference on Machine Learning and Natural Language Processing (MLNLP)
会议日期
2022-12-23 至 2022-12-25
论文集名
2022 5TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING, MLNLP 2022
发表日期
2022
起止页码
377-382
DOI
10.1145/3578741.3578832
收录
ISTP

作者

  • G

    Gu, Wenwen (通讯) (第一作者)

  • Q

    Qian, Haifeng

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417