基于多级可逆神经网络的大容量裁剪稳健型图像隐写技术  

High-capacity clipped robust image steganography based on multilevel invertible neural networks

作　　者：李泓萱 张松洋 任博 LI Hong-xuan;ZHANG Song-yang;REN Bo(College of Cyber Science,Nankai University,Tianjin 300381,China;Tianjin Media Computing Center,Tianjin 300381,China;TravelSky Technology Limited,Beijing 101318,China;College of Computer Science,Nankai University,Tianjin 300381,China)

机构地区：[1]南开大学网络空间安全学院,天津300381 [2]天津市媒体计算技术工程研究中心,天津300381 [3]中国民航信息网络股份有限公司,北京101318 [4]南开大学计算机学院,天津300381

出　　处：《图学学报》2023年第6期1149-1161,共13页Journal of Graphics

基　　金：中央高校基础研究经费项目(63233080)。

摘　　要：图像隐写技术是将秘密信息嵌入到载体图像中,以保护信息的机密性,并确保不被观察者察觉。然而,在传输过程中,由于分辨率限制,载密图像的边缘区域容易受到裁剪。因此,如何从边缘区域缺失的载密图像中恢复出有效的连续隐藏信息是一个值得研究的问题。同时,图像隐写技术的另一个挑战是如何在不被检测到的情况下增加信息的有效载荷容量。为了解决上述问题,提出了一种数据驱动的图像隐写算法方案。采用了一种大容量、裁剪稳健的多级双向映射的可逆隐写网络,能够从边缘破损的载密图像中尽可能完整地恢复出连续的秘密图像。此外,算法具有高度的灵活性,可以通过多层级联中改变图像分支的通道数量实现不同规格的大尺寸图像隐写。实验表明,在各种公开数据集上生成的载密图像的视觉隐蔽性、质量度量指标和裁剪恢复能力方面显著优于其他方法。Image steganography aims to safeguard information confidentiality by embedding secret information into carrier images while evading detection by observers.However,during the transmission,the edges of the carrier images are often prone to cropping due to resolution limitations,making it challenging to recover continuous hidden information from the edge-missing carrier images.Another challenge in image steganography is how to enhance the effective payload capacity without being detected.To address these challenges,we proposed a data-driven image steganography algorithm that employed a high-capacity and clipped robust multilevel invertible steganography network(CR-MISN).This network had the capability to recover the continuous secret images as fully as possible from carrier images with damaged edges.Furthermore,the algorithm exhibited a high degree of flexibility,allowing for the steganography of large-sized images with different specifications by altering channel numbers in the multilevel cascading of image branches.Experimental results demonstrated that the proposed method outperformed other state-of-the-art methods in terms of visual imperceptibility,quality metrics,and cropping recovery on various public datasets.

关 键 词：计算机视觉 大容量图像隐写技术 多级可逆神经网络 嵌套模块级联架构 图像裁剪稳健性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]