基于预处理层增强和注意力机制的空域图像隐写分析

doi:10.13229/j.cnki.jdxbgxb.20240437

摘要/Abstract

摘要：

为了更全面地捕获隐写操作对图像统计特征的改变，提高空域隐写分析的检测精度，本文结合隐写算法的嵌入特点，采用导数和Gabor双重滤波器对图像进行预处理，并对滤波器提取进行增强，产生多种残差图像，有效增加隐写分析特征的多样性。将优化的CBAM模块嵌入残差块中，引导网络有效聚焦于具有丰富隐写信号的区域，从而提高网络的判别学习能力和训练效果。将本模型与经典模型在BOSSbase v1.01和BOWS2两个公开数据集上进行比较，实验结果表明：该方法的检测精度优于现有主流模型Ye-Net、SRNet和ZhuNet。

关键词: 隐写分析, 卷积神经网络, 预处理层增强, 注意力模块

Abstract:

In order to capture the changes of statistical features of images caused by stegography more comprehensively and improve the detection accuracy of spatial steganalysis， the embedding characteristics of the steganographic algorithm are incorporated. The derivative and Gabor double filter is used to preprocess the image， and the filter extraction is enhanced to produce a variety of residual images， which effectively increases the diversity of steganographic features. The optimized CBAM module is embedded into the residual block to guide the network to effectively focus on the region with rich steganographic signals， thus strengthening the discriminant learning ability and training effect of the network. The proposed model is compared with the classical model on BOSSbase v1.01 and BOWS2， and the experimental results show that the detection accuracy of the proposed method is superior to the existing mainstream models of Ye-Net， SRNet and ZhuNet.

Key words: steganographic analysis, convolutional neural network, pretreatment layer enhancement, attention module

中图分类号:

TP309

罗维薇,刘长龙,雷琴. 基于预处理层增强和注意力机制的空域图像隐写分析[J]. 吉林大学学报(工学版), 2025, 55(12): 4024-4033.

Wei-wei LUO,Chang-long LIU,Qin LEI. Spatial image steganography based on preprocessing layer enhancement and attention mechanism[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(12): 4024-4033.

图/表 10

图1

表1

滤波器详细信息"

滤波器类型	基本权重	旋转角度/（ $°$ ）	滤波器数量/个
类别1	$D 1,0 = 0 ????? 0 ??? 0 1 - 1 ??? 0 0 ????? 0 ??? 0$	$90$	2
类别2	$D 1,1 = ???? 1 ?? - 1 - 1 ??????? 1 ?$	—	1
类别3	$D 2,0 = 0 ????? 0 ???? 0 1 - 2 ???? 1 0 ????? 0 ???? 0$	$90$	2
类别4	$D 2,1 = - 1 ?????? 2 ?? - 1 ???? 1 - 2 ??????? 1 ???? 0 ?????? 0 ??????? 0$	$90$	2
类别5	$D 3,0 = 0 ?????? 0 ??? 0 ?????? 0 ???? 0 ? 0 ?????? 0 ??? 0 ?????? 0 ???? 0 1 - 3 ??? 3 ? - 1 ???? 0 0 ?????? 0 ??? 0 ?????? 0 ???? 0 0 ?????? 0 ??? 0 ?????? 0 ???? 0$	$90$	2
类别6	$D 4,0 = 0 ?????? 0 ????? 0 ?????? 0 ???? 0 ? 0 ?????? 0 ????? 0 ?????? 0 ???? 0 1 - 4 ????? 6 - 4 ???? 1 0 ?????? 0 ????? 0 ?????? 0 ???? 0 0 ?????? 0 ????? 0 ?????? 0 ???? 0$	$90$	2
类别7	$D 4,2 = ????? 1 ? - 4 ???????? 6 ? - 4 ?????? 1 - 2 ?????? 8 - 12 ?????? 8 ? - 2 ???? 1 ? - 4 ????????? 6 ? - 4 ?????? 1 ???? 0 ?????? 0 ????????? 0 ?????? 0 ?????? 0 ???? 0 ?????? 0 ????????? 0 ?????? 0 ?????? 0$	$90$	2
类别8	$D 2,2 = ????? 1 ? - 2 ?????? 1 - 2 ??????? 4 ? - 2 ????? 1 ?? - 2 ????? 1$	—	1
类别9	$D 3,3 = ???? 1 ? - 3 ????? 3 ?? - 1 ? - 3 ????? 9 ? - 9 ??????? 3 ???? 3 ? - 9 ?????? 9 ? - 3 - 1 ????? 3 ? - 3 ??????? 1 ?$	—	1
类别10	$D 4,4 = ???? 1 ??? - 4 ???????? 6 ???? - 4 ??????? 1 - 4 ?????? 16 ? - 24 ?????? 16 - 4 ???? 6 - 24 ?????? 36 ?? - 24 ?????? 6 - 4 ?????? 16 - 24 ?????? 16 ?? - 4 ???? 1 ???? - 4 ???????? 6 ???? - 4 ?????? 1$	—	1

表1

表 2

图2

图3

图4

表3

表4

图5

表5

参考文献 27

[1]	Xiang S J, Luo X R. Reversible data hiding in encry pted image based on homomorphic public key crypt osystem[J]. Journal of Software, 2016, 27(6): 1592- 1601.
[2]	陈君夫, 付章杰, 张卫明, 等. 基于深度学习的图像隐写分析综述[J]. 软件学报,2021, 32(2): 551-578.
	Chen Jun-fu, Fu Zhang-jie, Zhang Wei-ming, et al. A review of image steganography based on deep learning [J]. Journal of Software, 2021, 32(2): 551-578.
[3]	Fridrich J, Kodovsky J. Rich models for steganalysis of digital images[J]. IEEE Transactions on Information Forensics and Security, 2012, 7(3): 868-882.
[4]	Holub V, Fridrich J. Low-complexity features for JPEG steganalysis using undecimated DCT[J]. IEEE Transactions on Information Forensics and Security, 2014, 10(2): 219-228.
[5]	Holub V, Fridrich J. Phase-aware projection model for steganalysis of JPEG images[C]∥Media Watermarking, Security, and Forensics,Philadelphia, USA,2015:75-84.
[6]	Khan A, Sohail A, Zahoora U,et al. A survey of the recent architectures of deep convolutional neural networks[J]. Artificial Intelligence Review, 2020, 53: 5455-5516.
[7]	Chollet F. Xception: deep learning with depthwise separable convolutions[C]∥Proc IEEE Conf Comput Vis Pattern Recognit (CVPR),Honolulu, USA, 2017: 1800-1807.
[8]	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]∥Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), Las Vegas,USA, 2016: 770-778.
[9]	Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-ResNet and he impact of residual connections on learning[C]∥AAAI Conf Artif Intell,San Francisco,USA, 2017: 4278-4284.
[10]	Qian Y, Dong J, Wang W, et al. Learning and transferring representations for image steganalysis using convolutional neural network[C]∥IEEE International Conference on Image Processing(ICIP), Phoenix, USA, 2016: 2752-2756.
[11]	Jian Y, Ni J, Yang Y.Deep learning hierarchical representations for image steganalysis[J].IEEE Trans. Inf Forensic Secur,2017,12 (11): 2545-2557.
[12]	Zhang X B, Zhang X P, Feng G. Image steganalysis network based on dual-attention mechanism[J]. IEEE Signal Processing Letters, 2023, 30: 1287-1291.
[13]	Qian Y, Dong J, Wang W, et al. Deep learning for steganalysis via convolutional neural networks[C]∥Media Watermarking, Security, and Forensics, San Francisco, USA, 2015: 171-180.
[14]	Xu G, Wu H Z, Shi Y Q. Structural design of convolutional neural networks for steganalysis[J]. IEEE Signal Processing Letters, 2016, 23(5): 708-712.
[15]	Ye J, Ni J, Yi Y. Deep learning hierarchical representations for image steganalysis[J]. IEEE Transactions on Information Forensics and Security, 2017, 12(11): 2545-2557.
[16]	Zhang R, Zhu F, Liu J, et al. Depth-wise separable convolutions and multi-level pooling for an efficient spatial CNN-based steganalysis[J]. IEEE Transactions on Information Forensics and Security, 2019, 15: 1138-1150.
[17]	Han X, Zhang T. Spatial steganalysis based on non-local block and multi-channel convolutional networks[J]. IEEE Access, 2022, 10: 87241-87253.
[18]	Li B, Li Z, Zhou S, et al. New steganalytic features for spatial image steganography based on derivative filters and threshold LBP operator[J]. IEEE Transactions on Information Forensics and Security, 2017, 13(5): 1242-1257.
[19]	史晓裕, 李斌, 谭舜泉. 深度学习空域隐写分析的预处理层[J]. 应用科学学报,2018, 36(2): 309-320.
	Shi Xiao-yu, Li Bin, Tan Shun-quan. Preprocessing layer for deep learning spatial steganography [J]. Chinese Journal of Applied Sciences, 2018, 36(2): 309-320.
[20]	Li B, Wei W, Ferreira A, et al. ReST-Net: diverse activation modules and parallel subnets-based CNN for spatial image steganalysis[J]. IEEE Signal Processing Letters, 2018, 25(5): 650-654.
[21]	Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 7132-7141.
[22]	Woo S, Park J, Lee J Y, et al. Cbam: convolutional block attention module[C]∥Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 2018: 3-19.
[23]	Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020:11531-11539.
[24]	Bas P, Filler T, Pevný T. Break our steganographic system: the ins and outs of organizing BOSS[C]∥International Workshop on Information Hiding, Prague, Czech Republic, 2011: 59-70.
[25]	Bas P, Furon T. BOWS-2. [DB/OL]. [2024-04-12]. .
[26]	He T, Zhang Z, Zhang H, et al. Bag of tricks for image classification with convolutional neural networks[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 558-567.
[27]	Boroumand M, Chen M, Fridrich J. Deep residual network for steganalysis of digital images[J]. IEEE Transactions on Information Forensics and Security, 2018, 14(5): 1181-1193.

相关文章 15

[1]	朴燕,康继元. RAUGAN：基于循环生成对抗网络的红外图像彩色化方法[J]. 吉林大学学报(工学版), 2025, 55(8): 2722-2731.
[2]	田婧,马社强,宋现敏,赵丹,陈发城. 稀疏数据下的交通状态估计自适应卷积网络[J]. 吉林大学学报(工学版), 2025, 55(8): 2579-2587.
[3]	肖红,刘显德. 基于混合智能的学习状态实时采集与动态分析方法[J]. 吉林大学学报(工学版), 2025, 55(7): 2402-2408.
[4]	冯志刚,王首起,于明月. 基于变分模态提取及轻量级网络的滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2025, 55(6): 1883-1891.
[5]	杜睿山,王紫珊. 基于时空注意力的多视角人脸表情识别算法[J]. 吉林大学学报(工学版), 2025, 55(6): 2097-2102.
[6]	胡宏宇,张争光,曲优,蔡沐雨,高菲,高镇海. 基于双分支和可变形卷积网络的驾驶员行为识别方法[J]. 吉林大学学报(工学版), 2025, 55(1): 93-104.
[7]	汪豪,赵彬,刘国华. 基于时间和运动增强的视频动作识别[J]. 吉林大学学报(工学版), 2025, 55(1): 339-346.
[8]	张锦洲,姬世青,谭创. 融合卷积神经网络和双边滤波的相贯线焊缝提取算法[J]. 吉林大学学报(工学版), 2024, 54(8): 2313-2318.
[9]	朱圣杰,王宣,徐芳,彭佳琦,王远超. 机载广域遥感图像的尺度归一化目标检测方法[J]. 吉林大学学报(工学版), 2024, 54(8): 2329-2337.
[10]	赵宏伟,武鸿,马克,李海. 基于知识蒸馏的图像分类框架[J]. 吉林大学学报(工学版), 2024, 54(8): 2307-2312.
[11]	特木尔朝鲁朝鲁,张亚萍. 基于卷积神经网络的无线传感器网络链路异常检测算法[J]. 吉林大学学报(工学版), 2024, 54(8): 2295-2300.
[12]	孙铭会,薛浩,金玉波,曲卫东,秦贵和. 联合时空注意力的视频显著性预测[J]. 吉林大学学报(工学版), 2024, 54(6): 1767-1776.
[13]	魏晓辉,王晨洋,吴旗,郑新阳,于洪梅,岳恒山. 面向脉动阵列神经网络加速器的软错误近似容错设计[J]. 吉林大学学报(工学版), 2024, 54(6): 1746-1755.
[14]	夏超,王梦佳,朱剑月,杨志刚. 基于分层卷积自编码器的钝体湍流流场降阶分析[J]. 吉林大学学报(工学版), 2024, 54(4): 874-882.
[15]	梁礼明,周珑颂,尹江,盛校棋. 融合多尺度Transformer的皮肤病变分割算法[J]. 吉林大学学报(工学版), 2024, 54(4): 1086-1098.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

算法	Original	Original + Mean
WOW	0.175 3	0.170 0
S-UNIWARD	0.214 2	0.206 5

模型类型	S-UNIWARD		WOW
模型类型	0.2 bpp	0.4 bpp	0.2 bpp	0.4 bpp
未加注意力机制的模型	0.256 5	0.137 2	0.199 5	0.114 0
添加CBAM的模型	0.207 8	0.120 8	0.170 8	0.099 7
添加CBAM+的模型	0.206 5	0.111 2	0.170 0	0.104 5

算法	BOSS	BOSS + BOWS2
算法	0.2 bpp 0.4 bpp	0.2 bpp 0.4 bpp
Ye-Net	0.291 6 0.213 6	0.256 9 0.142 9
SRNet	0.247 9 0.145 9	0.192 2 0.093 5
ZhuNet	0.221 8 0.121 7	0.173 5 0.087 4
本文算法	0.170 0 0.104 5	0.147 0 0.068 3