首页 | 本学科首页   官方微博 | 高级检索  
     检索      

深度模型水印
引用本文:张新鹏,吴汉舟.深度模型水印[J].自然杂志,2022,44(4):267-273.
作者姓名:张新鹏  吴汉舟
作者单位:上海大学 通信与信息工程学院,上海 200444
摘    要:深度神经网络模型凝结了设计者的智慧,需要消耗大量数据和计算资源,是人工智能技术的重要产出物,已被广泛应用于生产和生活当中。然而,作为一种数字产品,如何保护深度神经网络模型免于被非法复制、分发或滥用(即知识产权保护)是人工智能产业化进程中必须面临和解决的难题。文章主要介绍基于数字水印的深度模型产权保护技术,通过总结深度模型水印的发展现状,对深度模型水印的研究趋势进行展望。

关 键 词:深度模型  数字水印  产权保护  人工智能安全  
收稿时间:2022-04-27

Deep model watermarking
ZHANG Xinpeng,WU Hanzhou.Deep model watermarking[J].Chinese Journal of Nature,2022,44(4):267-273.
Authors:ZHANG Xinpeng  WU Hanzhou
Institution:School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
Abstract:Deep neural networks (DNNs) condense the wisdom of the designer and consume a lot of data and computing resources. It is an important artificial intelligence technology, and is widely applied in our daily life. However, as a digital asset, how to protect DNN models from being illegally copied, distributed or abused (that is, intellectual property protection) is a difficult problem that must be faced and solved in the process of artificial intelligence industrialization. This article reviews digital watermarking techniques for intellectual property protection of DNN models. By summarizing the development status of deep model watermarking, the research trend of deep model watermarking is further prospected.
Keywords:
点击此处可从《自然杂志》浏览原始摘要信息
点击此处可从《自然杂志》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号