A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism

作     者：Nannan Wu Xianyi Chen James Msughter Adeke Junjie Zhao 

作者机构：School of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing210044China School of Electronics and Information EngineeringNanjing University of Information Science and TechnologyNanjing210044China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第78卷第3期

页      面：3001-3019页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key R&D Program of China(Grant Number 2021YFB2700900) the National Natural Science Foundation of China(Grant Numbers 62172232,62172233) the Jiangsu Basic Research Program Natural Science Foundation(Grant Number BK20200039) 

主　　题：Deep image hiding attention mechanism privacy protection data security visual quality 

摘      要：Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information ***,these approaches have some *** example,a cover image lacks self-adaptability,information leakage,or weak *** address these issues,this study proposes a universal and adaptable image-hiding ***,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image ***,to improve perceived human similarity,perceptual loss is incorporated into the training *** experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality ***,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at ***,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.