文件名称:Protecting the Intellectual Property of Deep Neural Networks with Watermarking: The Frequency Domain Approach

  • 所属分类:
  • 报告论文
  • 资源属性:
  • [PDF]
  • 上传时间:
  • 2021-05-05
  • 文件大小:
  • 365.68kb
  • 下载次数:
  • 0次
  • 提 供 者:
  • bamzi334
  • 相关连接:
  • 下载说明:
  • 别用迅雷下载,失败请重下,重下不扣分!

介绍说明--下载内容均来自于网络,请自行研究使用

Similar to other digital assets, deep neural network
(DNN) models could suffer from piracy threat initiated by insider
and/or outsider adversaries due to their inherent commercial
value. DNN watermarking is a promising technique to mitigate
this threat to intellectual property. This work focuses on black-
box DNN watermarking, with which an owner can only verify
his ownership by issuing special trigger queries to a remote
suspicious model. However, informed attackers, who are aware
of the watermark and somehow obtain the triggers, could
forge fake triggers to claim their ownerships since the poor
robustness of triggers and the lack of correlation between the
model and the owner identity. This consideration calls for new
watermarking methods that can achieve better trade-off for
addressing the discrepancy. In this paper, we exploit frequency
domain image watermarking to generate triggers and build our
DNN watermarking algorithm accordingly. Since watermarking
in the frequency domain is high concealment and robust to
signal processing operation, the proposed algorithm is superior to
existing schemes in resisting fraudulent claim attack. Besides, ex-
tensive experimental results on 3 datasets and 8 neural networks
demonstrate that the proposed DNN watermarking algorithm
achieves similar performance on functionality metrics and better
performance on security metrics when compared with existing
algorithms.
(系统自动生成,下载前可以参看下载内容)

下载文件列表

压缩包 : 09343235.zip 列表
09343235.pdf

相关说明

  • 本站资源为会员上传分享交流与学习,如有侵犯您的权益,请联系我们删除.
  • 本站是交换下载平台,提供交流渠道,下载内容来自于网络,除下载问题外,其它问题请自行百度更多...
  • 请直接用浏览器下载本站内容,不要使用迅雷之类的下载软件,用WinRAR最新版进行解压.
  • 如果您发现内容无法下载,请稍后再次尝试;或者到消费记录里找到下载记录反馈给我们.
  • 下载后发现下载的内容跟说明不相乎,请到消费记录里找到下载记录反馈给我们,经确认后退回积分.
  • 如下载前有疑问,可以通过点击"提供者"的名字,查看对方的联系方式,联系对方咨询.

相关评论

暂无评论内容.

发表评论

*主  题:
*内  容:
*验 证 码:

源码中国 www.ymcn.org