结合融合特征与特征映射的空域图像隐写分析

doi:10.13229/j.cnki.jdxbgxb.20220402

吉林大学学报(工学版) ›› 2023, Vol. 53 ›› Issue (11): 3260-3267.doi: 10.13229/j.cnki.jdxbgxb.20220402

结合融合特征与特征映射的空域图像隐写分析

罗维薇¹(),刘少伟¹,张冰涛¹,李萌¹,刘海銮²(),樊凌雁²

^1.兰州交通大学电子与信息工程学院，兰州 730070
^2.杭州电子科技大学微电子研究院，杭州 310018

收稿日期:2022-04-12 出版日期:2023-11-01 发布日期:2023-12-06
通讯作者: 刘海銮 E-mail:luoweiwei@lzjtu.edu.cn;lloyd.liu@sage-micro.com.cn
作者简介:罗维薇（1977-），女，副教授，硕士.研究方向：图像处理，模式识别，人工智能.E-mail：luoweiwei@lzjtu.edu.cn
基金资助:
国家自然科学基金项目(61962034);浙江省科技计划项目(2020R52019)

Steganalysis of spatial image combining fusion features and feature mapping

Wei-wei LUO¹(),Shao-wei LIU¹,Bing-tao ZHANG¹,Meng LI¹,Hai-luan LIU²(),Ling-yan FAN²

^1.School of Electronic and Information Engineering，Lanzhou Jiaotong University，Lanzhou 730070，China
^2.Microelectronics Research Institute，Hangzhou Dianzi University，Hangzhou 310018，China

Received:2022-04-12 Online:2023-11-01 Published:2023-12-06
Contact: Hai-luan LIU E-mail:luoweiwei@lzjtu.edu.cn;lloyd.liu@sage-micro.com.cn

摘要/Abstract

摘要：

为了更好地捕获隐写术对图像统计特征的改变，提高对隐写图像的检测率并解决特征映射问题，提出结合融合特征与特征映射的隐写分析方法，提取融合特征，更全面地捕获隐写算法对载体图像统计特征的扰动。同时，提出结合PCA的特征映射，以解决图像数小于特征维数时不能直接投影的问题。然后，对融合特征进行结合PCA的近似映射，用于隐写分析。实验证明：该方法有效地提升了对隐写图像的检测率。

关键词: 隐写分析, 特征融合, 主成分降维, 特征映射

Abstract:

In order to better capture the changes of steganography to the statistical characteristics of images， improve the detection rate of steganographic images and solve the problem of feature mapping， a steganalysis method combining fusion features and feature mapping is proposed to extract fusion features and capture more comprehensively the perturbation of the steganographic algorithm to the statistical characteristics of the carrier image. And a feature map combined with PCA is proposed to solve the problem of direct projection when the number of images is less than the feature dimension. The fused features are then subjected to approximate mapping combined with PCA for steganalysis. Experiments show that this method can effectively improve the detection rate of steganographic images.

Key words: steganalysis, feature fusion, PCA dimensionality reduction, feature mapping

中图分类号:

TP309

罗维薇,刘少伟,张冰涛,李萌,刘海銮,樊凌雁. 结合融合特征与特征映射的空域图像隐写分析[J]. 吉林大学学报(工学版), 2023, 53(11): 3260-3267.

Wei-wei LUO,Shao-wei LIU,Bing-tao ZHANG,Meng LI,Hai-luan LIU,Ling-yan FAN. Steganalysis of spatial image combining fusion features and feature mapping[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(11): 3260-3267.

图/表 4

图1

图2

表1

图3

参考文献 22

1	Xiang S J, Luo X R. Reversible data hiding in encrypted image based on homomorphic public key cryptosystem[J]. Journal of Software, 2016, 27(6): 1592-1601.
2	Li Y F, Ding L P, Wu J Z, et al. Survey on key issues in networks covert channel[J]. Journal of Software, 2019, 30(8): 2470-2490.
3	栗风永. 数字图像高维特征隐写分析及安全隐写[D]. 上海: 上海大学通信学院, 2014.
	Su Feng-yong. Steganalysis with high dimensional features and secure steganography in digital image[D]. Shangai: School of Communication, Shanghai University, 2014.
4	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. Review of image steganalysis based on deep learning[J]. Journal of Software, 2021,32(2): 551-578.
5	Westfld A, Pfitzmanna A. Attacks on steganographic systems[C]∥Proceedings of the Third International Workshop on Information Hiding, Berlin, Germany, 1999: 61-76.
6	Ker A D. Steganalysis of LSB matching in grayscale images[J]. IEEE Signal Processing Letters, 2005, 12(6): 441-444.
7	Pevny T, Bas P, Fridrich J. Steganalysis by subtractive pixel adjacency matrix[J]. IEEE Transactions on information Forensics and Security, 2010, 5(2): 215-224.
8	Fridrich J, Kodovsky J. Rich models for steganalysis of digital images [J]. IEEE Transactions on Information Forensics and Security, 2012, 7(3): 868-882.
9	Holub V, Fridrich J. Random projections of residuals for digital image steganalysis[J]. IEEE Transactions on Information Forensics and Security, 2013, 8(12): 1996-2006.
10	Denemark T, Sedighi V, Holub V, et al. Selection-channel-aware rich model for steganalysis of digital images[C]∥Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, Atlanta, USA, 2014: 48-53.
11	Denemark T, Fridrich J, Comesaña-alfaro P. Improving selection-channel-aware steganalysis features [J]. Electronic Imaging, 2016(8): 1-8.
12	Chang C C, Lin C J. LIBSVM: a library for support vector machines [J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1-27.
13	Kodovsky J, Fridrich J, Holub V. Ensemble classifiers for steganalysis of digital media[J]. IEEE Transactions on Information Forensics and Security, 2011, 7(2): 432-444.
14	Cogranne R, Sedighi V, Fridrich J, et al. Is ensemble classifier needed for steganalysis in high-dimensional feature spaces?[C]∥Proceedings of the 2015 IEEE International Workshop on Information Forensics and Security, Rome, Italy, 2015: 1-6.
15	Boroumand M, Fridrich J. Applications of explicit non-linear feature maps in steganalysis[J]. IEEE Transactions on Information Forensics and Security, 2017, 13(4): 823-833.
16	邓利芳, 党建武, 王阳萍, 等. 结合混合核特征映射的空域图像隐写分析[J]. 计算机工程与应用, 2021, 57(9): 118-125.
	Deng Li-fang, Dang Jian-wu, Wang Yang-ping, et al. Steganalysis of spatial image based on hybrid kernel feature mapping[J]. Computer Engineering and Applications, 2021, 57(9): 118-125.
17	刘富, 宗宇轩, 康冰, 等, 基于优化纹理特征的手背静脉识别系统 [J]. 吉林大学学报: 工学版, 2018, 48(6): 1844-1850.
	Liu Fu, Zong Yu-xuan, Kang Bing, et al. Dorsal hand vein recognition system based on optimized texture features[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(6): 1844-1850.
18	Huang D S, Jiang F W, Li K P, et al. Scaled PCA: a new approach to dimension reduction[J/OL]. [2022-04-02].
19	刘云, 刘富, 侯涛, 等. 优化核参数的模糊C均值聚类算法[J]. 吉林大学学报: 工学版, 2016, 46(1): 246-251.
	Liu Yun, Liu Fu, Hou Tao, et al. Kernel-based fuzzy C-means clustering method based on parameter optimization[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(1): 246-251.
20	Denemark T, Fridrich J, Holub V. Further study on the security of S-UNIWARD[J]. Media Watermarking, Security, and Forensics, 2014, 9028: 902805.
21	Holub V, Fridrich J. Designing steganographic distortion using directional filters[C]∥ IEEE International Workshop on Information Forensicsand Security, Adeje, Spain, 2012: 234-239.
22	Sedighi V, Fridrich J, Cogranne R. Content-adaptive pentary steganography using the multivariate generalized Gaussian cover model[J]. Media Watermarking, Security, and Forensics, 2015, 9409: 94090H.

相关文章 15

[1]	刘培勇,董洁,谢罗峰,朱杨洋,殷国富. 基于多支路卷积神经网络的磁瓦表面缺陷检测算法[J]. 吉林大学学报(工学版), 2023, 53(5): 1449-1457.
[2]	欧阳宁,李祖锋,林乐平. 基于多层次空⁃谱融合网络的高光谱图像分类[J]. 吉林大学学报(工学版), 2022, 52(10): 2438-2446.
[3]	潘晓英,魏德,赵逸喆. 基于Mask R⁃CNN和上下文卷积神经网络的肺结节检测[J]. 吉林大学学报(工学版), 2022, 52(10): 2419-2427.
[4]	周大可,张超,杨欣. 基于多尺度特征融合及双重注意力机制的自监督三维人脸重建[J]. 吉林大学学报(工学版), 2022, 52(10): 2428-2437.
[5]	赵宏伟,霍东升,王洁,李晓宁. 基于显著性检测的害虫图像分类[J]. 吉林大学学报(工学版), 2021, 51(6): 2174-2181.
[6]	谌华,郭伟,闫敬文,卓文浩,吴良斌. 基于深度学习的SAR图像道路识别新方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1778-1787.
[7]	倪涛,刘海强,王林林,邹少元,张红彦,黄玲涛. 基于双向长短期记忆模型的起重机智能操控方法[J]. 吉林大学学报(工学版), 2020, 50(2): 445-453.
[8]	王生生, 郭湑, 张家晨, 王光耀, 赵欣. 基于全局与局部形状特征融合的形状识别算法[J]. 吉林大学学报(工学版), 2016, 46(5): 1627-1632.
[9]	张浩, 刘海明, 吴春国, 张艳梅, 赵天明, 李寿涛. 基于多特征融合的绿色通道车辆检测判定[J]. 吉林大学学报(工学版), 2016, 46(1): 271-276.
[10]	杨欣，刘加，周鹏宇，周大可. 基于多特征融合的粒子滤波自适应目标跟踪算法[J]. 吉林大学学报(工学版), 2015, 45(2): 533-539.
[11]	吴迪, 曹洁. 智能环境下基于核相关权重鉴别分析算法的多特征融合人脸识别[J]. 吉林大学学报(工学版), 2013, 43(02): 439-443.
[12]	王新颖, 刘钢, 谷方明, 肖巍. 三维模型检索中的语义与形状异构特征融合[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 359-363.
[13]	邢笑雪, 刘富, 马冬梅, 翟微微, 王芳荣. 基于机器视觉的软体纤维丝集束智能计数系统[J]. , 2012, 42(05): 1267-1272.
[14]	曲智国, 王平, 高颖慧, 王鹏, 沈振康, 李江. 基于同化核分割相同值区域特征融合的边缘检测 [J]. , 2012, (03): 759-765.
[15]	陈绵书, 付平, 李勇, 张慧. 基于范围相似分最小化的图像特征融合[J]. 吉林大学学报(工学版), 2010, 40(增刊): 365-0368.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

算法	特征	有效载荷payload/bpp
算法	特征	0.1	0.2	0.3	0.4	0.5
S-UNIWARD	SRM	0.3651	0.2933	0.2397	0.1921	0.1562
	SPAM	0.4133	0.3329	0.2983	0.2494	0.2261
	SRM近似映射	0.3626	0.2765	0.2192	0.1709	0.1353
	本文方法	0.3281	0.2354	0.1946	0.1592	0.1237
WOW	SRM	0.3028	0.2314	0.1916	0.1534	0.1297
	SPAM	0.3542	0.2928	0.2601	0.2321	0.2013
	SRM近似映射	0.2884	0.2093	0.1602	0.1338	0.1086
	本文方法	0.2623	0.1864	0.1537	0.1301	0.1055
MVG	SRM	0.4089	0.3291	0.2788	0.2215	0.1908
	SPAM	0.4673	0.3894	0.3531	0.3152	0.2896
	SRM近似映射	0.4063	0.3041	0.2692	0.2177	0.1772
	本文方法	0.3902	0.2895	0.2542	0.2103	0.1684

结合融合特征与特征映射的空域图像隐写分析

Steganalysis of spatial image combining fusion features and feature mapping

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 22

相关文章 15

Metrics

本文评价

推荐阅读 10