版权说明 操作指南
首页 > 成果 > 详情

'Identity Bracelets' for Deep Neural Networks

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Xu, Xiangrui;Li, Yaqin;Yuan, Cao*
通讯作者:
Yuan, Cao
作者机构:
[Xu, Xiangrui; Li, Yaqin; Yuan, Cao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
通讯机构:
[Yuan, Cao] W
Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
语种:
英文
关键词:
Deep neural network;ownership verification;security and privacy;serial number;watermarking
期刊:
IEEE ACCESS
ISSN:
2169-3536
年:
2020
卷:
8
页码:
102065-102074
基金类别:
China NSFCNational Natural Science Foundation of China (NSFC) [F060609]
机构署名:
本校为第一且通讯机构
院系归属:
数学与计算机学院
摘要:
The power of deep learning and the enormous effort and money required to build a deep learning model makes stealing them a hugely worthwhile and highly lucrative endeavor. Worse still, model theft requires little more than a high-school understanding of computer functions, which ensures a healthy and vibrant black market full of choice for any would-be pirate. As such, estimating how many neural network models are likely to be illegally reproduced and distributed in future is almost impossible. Therefore, we propose an embedded & x2018;identity bracelet & x2019; for deep neural networks that a...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com