生成图水印的前沿研究与展望  

Frontier research and prospect of watermarking for generated images

作　　者：王金伟[1,2,3] 姜晓丽 谭贵峰 罗向阳[5] WANG Jinwei;JIANG Xiaoli;TAN Guifeng;LUO Xiangyang(Engineering Research Center of Digital Forensics,Ministry of Education,Nanjing University of Information Science and Technology,Nanjing 210044,China;Department of Computer and Cyberspace Security,Nanjing University of Information Science and Technology,Nanjing 210044,China;Department of Software,Nanjing University of Information Science and Technology,Nanjing 210044,China;State Key Laboratory of Mathematical Engineering and Advanced Computing,Zhengzhou 450001,China;Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]南京信息工程大学数字取证教育部工程研究中心,南京210044 [2]南京信息工程大学计算机学院、网络空间安全学院,南京210044 [3]南京信息工程大学软件学院,南京210044 [4]数学工程与先进计算国家重点实验室,郑州450001 [5]信息工程大学,郑州450001

出　　处：《网络空间安全科学学报》2024年第1期50-62,共13页Journal of Cybersecurity

基　　金：国家自然科学基金(62072250,62172435,U1804263,U20B2065,61872203,71802110,61802212);中原科技创新领军人才项目(214200510019);江苏省自然科学基金(BK20200750);河南省网络空间态势感知重点实验室开放基金(HNTS2022002);江苏省研究生研究与实践创新项目(KYCX200974);广东省信息安全技术重点实验室开放项目(2020B1212060078);山东省计算机网络重点实验室开放课题基金(SDKLCN-2022-05)。

摘　　要：随着人工智能生成内容(Artificial Intelligence Generated Content,AIGC)带来的深度合成浪潮,数字水印技术作为图像取证领域中的一种主动防御手段,被广泛应用于识别生成内容和模型的版权保护。因此,生成图水印越来越受到研究者的关注。首先,介绍了生成图水印的研究背景,从模型版权保护和AIGC监管两个角度介绍生成图水印的研究动机。接着,基于生成模型和水印技术的发展引出了生成图水印问题,将水印根据是否参与生成过程分为两类,并对这两类生成图水印的现状进行了详细的梳理和介绍。随后,对现有的生成图水印方法进行评估,在传统水印需满足的鲁棒性、不可察觉性和容量基础上,进一步提出了针对生成图水印的新要求。最后,指出生成图水印中有待进一步解决的问题及发展趋势。With the wave of deep synthesis brought about by AIGC(Artificial Intelligence Generative Content),digital watermark-ing technology was widely used to identify the copyright protection of generated content and models as an active defense method in the field of image forensics.Therefore,generating image watermarks had attracted more and more attention from researchers.Firstly,the re-search background of generative image watermarking was introduced,and the research motivation of generative image watermarking was introduced from the perspectives of model copyright protection and AIGC supervision.Then,based on the development of genera-tion model and watermarking technology,the problem of generating image watermarks was introduced,and the watermarks were divid-ed into two categories according to whether they participated in the generation process,and the current status of these two types of gener-ated image watermarks was sorted out and introduced in detail.Subsequently,the existing methods of generating image watermarks were evaluated.On the basis of the robustness,imperceptibility and capacity of traditional watermarks,new requirements for generating im-age watermarks were further proposed.Finally,the problems and development trends that needed to be further solved in the generation of image watermarks were pointed out.

关 键 词：版权保护 水印 生成模型 生成图 人工智能生成内容 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]