面向可逆图像处理网络的可证安全自然隐写  

Image processing network-inverted identifiable secure natural steganography

作　　者：王健[1,2,3] 陈可江[1,2,3] 张卫明 俞能海 Wang Jian;Chen Kejiang;Zhang Weiming;Yu Nenghai(School of Cyber Science and Technology,University of Science and Technology of China,Hefei 230027,China;Key Laboratory of Electromagnetic Space Information,Chinese Academy of Sciences,Hefei 230027,China;Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation,Hefei 230027,China)

机构地区：[1]中国科学技术大学网络空间安全学院,合肥230027 [2]中国科学院电磁空间信息重点实验室,合肥230027 [3]网络空间安全态势感知与评估安徽省重点实验室,合肥230027

出　　处：《中国图象图形学报》2023年第3期749-759,共11页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62102386,62002334,62072421,62121002);中国博士后科学基金项目(2021M693091);网络空间安全态势感知与评估安徽省重点实验室开放基金项目;中央高校基本科研业务费专项资金资助(WK2100000018)。

摘　　要：目的自然隐写是一种基于载体源转换的图像隐写方法,基本思想是使隐写后的图像具有另一种载体的特征,从而增强隐写安全性。但现有的自然隐写方法局限于对图像ISO(International Standardization Organization)感光度进行载体源转换,不仅复杂度高,而且无法达到可证安全性。为了提高安全性,本文结合基于标准化流的可逆图像处理模型,在隐空间完成载体源转换,同时通过消息映射的设计做到了可证安全的自然隐写。方法利用目前发展迅速的基于可逆网络的图像处理方法将图像可逆地映射到隐空间,通过替换使用的隐变量完成载体源的转换,从而避免对原始图像复杂的建模。同时,改进了基于拒绝采样的消息映射方法,简单地从均匀分布中采样以获得需要的条件分布,高效地将消息嵌入到隐变量中,并且保证了嵌入消息后的分布与原本使用的分布一致,从而实现了可证安全的自然隐写。结果针对图像质量、隐写容量、消息提取准确率、隐写安全性和运行时间进行了实验验证,结果表明在使用可逆缩放网络和可逆去噪网络时能够在每个像素值上平均嵌入5.625 bit消息,且具有接近99%的提取准确率,同时隐写分析网络SRNet(steganalysis residual network)和Zhu-Net的检测准确率都在50%附近,即相当于随机猜测。结论本文提出的隐写框架利用可逆图像处理网络实现了可证安全的自然隐写,在隐写容量和安全性上都具有很大优势。Objective Natural steganography is regarded as a cover-source switching based image steganography method.To enhance the steganographic security,its objective is focused on more steganographic image-related cover features.Natural steganography is originally designed for ISO(International Standardization Organization)sensitivity through adding noise to a low ISO image to yield a high ISO image feature,and modeling this noise signal to complete the message embedding.This approach is required for modeling the generation of ISO sensor noise,the development pipeline from raw sensor data stored in RAW format is commonly used like portable network graphics(PNG)or joint photographic experts group(JPEG)format images,which is very complex and not precise enough and the existing natural steganography approaches cannot be identified for safety inefficiently.To make the stylized images generated by steganography indistinguishable from other stylized images,some existing approaches are employed to explore steganography on the basis of image style transformation.However,it is challenged that the steganography-generated stylized image has the same distribution as the stylized image from another source,and none of them is as secure as traditional natural steganography.Actually,it is possible to achieve clarified security via using generated images as the cover image.Steganography is tackled for stronger invisibility than cryptography,but it has been difficult to achieve identifiable security,and most of methods are constrained of empirical security.Due to existing identifiable secure methods is required to obtain the distribution of cover datasets or the ability to sample from the cover distribution accurately,it is not feasible for traditional cover datasets.However,datasets-generated are easy to exact sampling because generative models random variables are required to be introduced to manipulate data generation.Therefore,to accomplish cover-source switching in latent space,and achieve identifiable secure natural steganography,th

关 键 词：隐写 自然隐写 可证安全隐写 可逆神经网络(INN) 图像处理 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]