DDAC:面向卷积神经网络图像隐写分析模型的特征提取方法  

DDAC:a feature extraction method for model of image steganalysis based on convolutional neural network

作　　者：王晓丹[1] 李京泰 宋亚飞[1] WANG Xiaodan;LI Jingtai;SONG Yafei(Air and Missile Defense College,Air Force Engineering University,Xi’an 710051,China)

机构地区：[1]空军工程大学防空反导学院,陕西西安710051

出　　处：《通信学报》2022年第5期68-81,共14页Journal on Communications

基　　金：国家自然科学基金资助项目(No.61876189)。

摘　　要：针对基于卷积神经网络的图像隐写分析方法中使用人工设计的滤波器在特征提取过程中有效性低的问题,提出方向差分自适应组合(DDAC)特征提取方法。在计算中心像素与周围不同方向像素的差分后,使用1×1卷积对方向差分进行线性组合。根据损失对组合参数自适应更新来构建多样化的滤波器,使获取的嵌入信息残差特征更有效。使用截断线性单元提高嵌入信息残差和图像信息残差的比率,加快模型收敛速度并提高残差特征提取能力。实验结果表明,该方法使Ye-net、Yedroudj-net模型的准确率在WOW和S-UNIWARD数据集中提高1.30%~8.21%。与固定和更新参数SRM滤波器方法相比,测试模型在不同隐写数据集中的准确率提高0.60%~20.72%,并且训练过程更稳定。对比其他图像隐写分析模型,DDAC-net具有更高的隐写分析效率。To solve the problem that for image steganalysis based on convolution neural network,manual designed filter kernels were used to extract residual characteristics,but in practice,these kernels filter were not suitable for each steganography algorithm and have worse performance in application,a directional difference adaptive combination(DDAC)method was proposed.Firstly,the difference was calculated between center pixel and each directional pixel around,and 1×1 convolution was adopted to achieve linear combinations of directional difference.Since the combination parameters self-adaptively update according to loss function,filter kernels could be more effective in extracting diverse residual characteristics of embedding information.Secondly,truncated linear unit(TLU)was applied to raise the ratio of embedding information residual to image information residual.The model’s coveragence was accelerated and the ability of feature extraction was promoted.Experimental results indicate that substituting the proposed method could improve the accuracy of Ye-net and Yedroudj-net by 1.30%~8.21%in WOW and S-UNIWARD datasets.Compared with fix and adjustable SRM filter kernels methods,the accuracy of test model using DDAC increases 0.60%~20.72%in various datasets,and the training progress was more stable.DDAC-net was proved to be more effective in comparsion with other steganalysis model.

关 键 词：图像隐写分析 卷积神经网络 特征提取 隐写分析富模型 截断线性单元 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]