基于特征选择和图卷积表示的JPEG图像隐写者识别

doi:10.11959/j.issn.1000-436x.2023128

Abstract

Abstract:

Aiming at the problem that the feature dimension of JPEG image steganalysis is too high, which leads to the complexity of distance calculation between users and a decrease in the identification performance of the steganographer, a method for steganographer recognition based on feature selection and graph convolutional representation was proposed.Firstly, the steganalysis features of the user’s images were extracted, and the feature subset with highseparability was selected.Then, the users were represented as a graph, and the features of users were obtained by training the graph convolutional neural network.Finally, because inter-class separability and intra-class aggregation were considered, the features of users that could capture the differences between users were learned.For steganographers who use JPEG steganography, such as nsF5, UED, J-UNIWARD, and so on, to embed secret information in images, the proposed method can reduce the feature dimensions and computing.The identification accuracy of various payloads can reach more than 80.4%, and it has an obvious advantage at the low payload.

Key words: steganalysis, steganographer identification, information hiding, JPEG image

CLC Number:

TP391

Qianqian ZHANG, Yi ZHANG, Hao LI, Yuanyuan MA, Xiangyang LUO. Steganographer identification of JPEG image based on feature selection and graph convolutional representation[J]. Journal on Communications, 2023, 44(7): 218-229.

Figures/Tables 13

隐写检测特征	特征维度	存储空间/GB	训练时间/s	识别准确率
CCPev^[18]	548	24.6	4445	52.9%
Pev^[17]	274	12.2	3036	50.2%
	250	11.2	2 911	51.17%
	200	9	2 703	50.6%
本文方法	150	6.6	2 659	79.2%
	100	4.5	2 635	$100 %$
	50	2.2	2 339	$100 %$

References 32

[1]	FENG G R , ZHANG X P , REN Y L ,et al. Diversity-based cascade filters for JPEG steganalysis[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020,30(2): 376-386.
[2]	WANG P , LIU F L , YANG C F . Towards feature representation for steganalysis of spatial steganography[J]. Signal Processing, 2020,169:107422.
[3]	KER A D , BAS P , B?HME R , et al . Moving steganography and steganalysis from the laboratory into the real world[C]// Proceedings of the 1st ACM Workshop on Information Hiding and Multimedia Security. New York:ACM Press, 2013: 45-58.
[4]	YOUSFI Y , DWORETZKY E , FRIDRICH J . Detector-informed batch steganography and pooled steganalysis[C]// Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security. New York:ACM Press, 2022: 157-168.
[5]	ZHONG N , QIAN Z X , WANG Z C ,et al. Batch steganography via generative network[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021,31(1): 88-97.
[6]	KER A D , PEVNY T . A new paradigm for steganalysis via clustering[C]// Proceedings of Media Watermarking,Security,and Forensics. Manchester:SPIE Publications, 2011: 312-324.
[7]	KER A D , PEVNY T . The steganographer is the outlier:realistic large-scale steganalysis[J]. IEEE Transactions on Information Forensics and Security, 2014,9(9): 1424-1435.
[8]	MAHMOUD H . Digital media steganography[M]. Amsterdam: Elsevier, 2020.
[9]	ZHENG M J , JIANG J M , WU S T ,et al. Content-adaptive selective steganographer detection via embedding probability estimation deep networks[J]. Neurocomputing, 2019,365: 336-348.
[10]	ZHENG M J , ZHONG S H , WU S T ,et al. Steganographer detection via deep residual network[C]// Proceedings of 2017 IEEE International Conference on Multimedia and Expo (ICME). Piscataway:IEEE Press, 2017: 235-240.
[11]	LI F Y , WU K , LEI J S ,et al. Steganalysis over large-scale social networks with high-order joint features and clustering ensembles[J]. IEEE Transactions on Information Forensics and Security, 2016,11(2): 344-357.
[12]	LI F Y , WEN M , LEI J S ,et al. Efficient steganographer detection over social networks with sampling reconstruction[J]. Peer-to-Peer Networking and Applications, 2018,11(5): 924-939.
[13]	LI L , ZHANG W M , CHEN K J ,et al. Side channel steganalysis:when behavior is considered in steganographer detection[J]. Multimedia Tools and Applications, 2019,78(7): 8041-8055.
[14]	LI L , ZHANG W M , CHEN K J ,et al. Steganographic security analysis from side channel steganalysis and its complementary attacks[J]. IEEE Transactions on Multimedia, 2020,22(10): 2526-2536.
[15]	ZHANG Z , ZHENG M J , ZHONG S H ,et al. Steganographer detection via enhancement-aware graph convolutional network[C]// Proceed ings of 2020 IEEE International Conference on Multimedia and Expo (ICME). Piscataway:IEEE Press, 2020: 1-6.
[16]	ZHANG Z , ZHENG M J , ZHONG S H ,et al. Steganographer detection via a similarity accumulation graph convolutional network[J]. Neural Networks, 2021,136: 97-111.
[17]	PEVNY T , FRIDRICH J . Merging Markov and DCT features for multi-class JPEG steganalysis[C]// Proceedings of Security,Steganography,and Watermarking of Multimedia Contents. Manchester:SPIE Publications, 2007: 28-40.
[18]	KODOVSKY J , FRIDRICH J . Calibration revisited[C]// Proceedings of the 11th ACM Workshop on Multimedia and Security. New York:ACM Press, 2009: 63-74.
[19]	FILLER T , JUDAS J , FRIDRICH J . Minimizing additive distortion in steganography using syndrome-trellis codes[J]. IEEE Transactions on Information Forensics and Security, 2011,6(3): 920-935.
[20]	HOLUB V , FRIDRICH J . Low-complexity features for JPEG steganalysis using undecimated DCT[J]. IEEE Transactions on Information Forensics and Security, 2015,10(2): 219-228.
[21]	XIA C , GUAN Q X , ZHAO X F ,et al. Improved JPEG phase-aware steganalysis features using multiple filter sizes and difference images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020,30(11): 4100-4113.
[22]	夏超, 刘亚奇, 关晴骁 ,等. 基于非线性残差的 JPEG 图像隐写分析[J]. 通信学报, 2023,44(1): 142-152.
	XIA C , LIU Y Q , GUAN Q X ,et al. Steganalysis of JPEG images using non-linear residuals[J]. Journal on Communications, 2023,44(1): 142-152.
[23]	CHEN Y W , LIN C J . Combining SVMs with various feature selection strategies[M]. Berlin: Springer, 2006.
[24]	GUO L J , NI J Q , SHI Y Q . Uniform embedding for efficient JPEG steganography[J]. IEEE Transactions on Information Forensics and Security, 2014,9(5): 814-825.
[25]	KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks[J]. arXiv Preprint,arXiv:1609.02907, 2016.
[26]	李永豪, 胡亮, 张平 ,等. 基于动态图拉普拉斯的多标签特征选择[J]. 通信学报, 2020,41(12): 47-59.
	LI Y H , HU L , ZHANG P ,et al. Multi-label feature selection based on dynamic graph Laplacian[J]. Journal on Communications, 2020,41(12): 47-59.
[27]	WEN Y D , ZHANG K P , LI Z F ,et al. A discriminative feature learning approach for deep face recognition[C]// European Conference on Computer Vision. Cham:Springer, 2016: 499-515.
[28]	BAS P , FILLER T , PEVNY T . “Break our steganographic system”:the ins and outs of organizing BOSS[C]// Proceedings of the 13th international Conference on Information Hiding. New York:ACM Press, 2011: 59-70.
[29]	PIVA A , BARNI M . The first BOWS contest:break our watermarking system[C]// Proceedings of Security,Steganography,and Watermarking of Multimedia Contents. Manchester:SPIE Publications, 2007: 425-434.
[30]	FRIDRICH J , PEVNY T , KODOVSKY J . Statistically undetectable jpeg steganography:dead ends challenges,and opportunities[C]// Pro ceedings of the 9th Workshop on Multimedia and Security. New York:ACM Press, 2007: 3-14.
[31]	HOLUB V , FRIDRICH J , DENEMARK T . Universal distortion function for steganography in an arbitrary domain[J]. EURASIP Journal on Information Security, 2014,2014(1): 1-13.
[32]	KER A D , PEVNY T . Batch steganography in the real world[C]// Proceedings of the Workshop on Multimedia and Security. New York:ACM Press, 2012: 1-10.

Metrics

Recommended 0

No Suggested Reading articles found!

嵌入率/bpnzAC	隐写检测特征	特征维度/维		特征分量个数（占比）
嵌入率/bpnzAC	隐写检测特征	特征维度/维	r = 0	r=10^-1	r=10^-9
0.2	Pev-274	274	5 (1.8%)	94 (34.3%)	160 (58.4%)
	CCPev	548	205 (37.4%)	354 (64.5%)	432 (78.8%)
	DCTR	8 000	338 (4%)	2 450 (30.6%)	3 619 (45.2%)
	DCTR₃	390	1 (0%)	160 (41.0%)	230 (59.0%)
	DCTR₄	1 050	4 (0.3%)	423 (40.3%)	604 (57.5%)
0.5	Pev-274	274	5 (1.8%)	41 (15.0%)	76 (27.8%)
	CCPev	548	203 (37.0%)	302 (55.1%)	343 (62.6%)
	DCTR	8 000	269 (3.3%)	672 (8.4%)	1 073 (13.4%)
	DCTR₃	390	0 (0%)	48 (12.3%)	72 (18.5%)
	DCTR₄	1 050	0 (0%)	99 (9.0%)	154 (14.7%)
0.8	Pev-274	274	5 (1.8%)	19 (6.9%)	36 (13.2%)
	CCPev	548	202 (36.8%)	272 (49.6%)	301 (54.9%)
	DCTR	8 000	269 (3.3%)	414 (5.1%)	485 (6.1%)
	DCTR₃	390	0 (0)	40 (10.2%)	50 (12.8%)
	DCTR₄	1 050	0 (0)	74 (7.0%)	90 (8.6%)

名称	值
图像数据库	BOSSbase-1.01，BOWs
图像大小	256像素×256像素，512像素×512像素
图像格式	JPEG
质量因子	75
图像颜色	灰度
隐写算法	nsF5，UED，J-UNIWARD
批量隐写策略	Even
嵌入率/bpnzAC	0.2，0.3，0.4，0.5
载体图像数量/幅	40 000（256像素×256像素）
	20 000（512像素×512像素）
载密图像数量/幅	3×4×40 000（256像素×256像素）
	3×4×20 000（512像素×512像素）

隐写方法	隐写检测特征	特征维度/维	识别准确率
隐写方法	隐写检测特征	特征维度/维	0.2 bpnzAC	0.3 bpnzAC	0.4 bpnzAC	0.5 bpnzAC
nsF5	CCPev^[18]	548	79%	82%	100%	100%
	Pev^[17]	274	68%	79%	100%	100%
	Ours	50	86%	100%	100%	100%
UED	CCPev^[18]	548	50.1%	50.1%	52.9%	100%
	Pev^[17]	274	52.8%	52.8%	50.2%	100%
	本文方法	50	80.4%	90.7%	100%	100%
J-UNIWARD	CCPev^[18]	548	51%	55%	58%	62%
	Pev^[17]	274	51%	52%	51%	56%
	DCTR^[20]	8000	51%	55%	56%	58%
	DCTR4^[21]	1050	52%	59%	61%	67%
	本文方法	50	83%	98%	100%	100%

Steganographer identification of JPEG image based on feature selection and graph convolutional representation

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 32

Related Articles 15

Metrics

Recommended 0

[1]	Dongyan HUANG, Kun LI. Research on multi-address time-based blockchain covert communication method [J]. Journal on Communications, 2023, 44(2): 148-159.
[2]	Chao XIA, Yaqi LIU, Qingxiao GUAN, Xin JIN, Yanshuo ZHANG, Shengwei XU. Steganalysis of JPEG images using non-linear residuals [J]. Journal on Communications, 2023, 44(1): 142-152.
[3]	Hui LI, Jiali JIN, Shuyu JIN, Weijiao MA. Text steganography method based on automatic selection coding and dynamic word selection strategy [J]. Journal on Communications, 2022, 43(9): 240-253.
[4]	Xiaodan WANG, Jingtai LI, Yafei SONG. DDAC: a feature extraction method for model of image steganalysis based on convolutional neural network [J]. Journal on Communications, 2022, 43(5): 68-81.
[5]	Zhen ZHANG, Jiaming NI, Ye YAO, Lichun GONG, Yujuan WANG, Guohua WU. Text coverless information hiding method based on synonyms expansion and label delivery mechanism [J]. Journal on Communications, 2021, 42(9): 173-183.
[6]	Zhili ZHOU, Meimin WANG, Gaobo YANG, Jianyu ZHU, Xingming SUN. Generative steganography method based on auto-generation of contours [J]. Journal on Communications, 2021, 42(9): 144-154.
[7]	Guohua WU,Lichun GONG,Lifeng YUAN,Ye YAO. Review of information hiding on Chinese text [J]. Journal on Communications, 2019, 40(9): 145-156.
[8]	Shuai REN,Zhen WANG,Dongxu SU,Tao ZHANG,Dejun MU. Information hiding algorithm based on mapping and structure data of 3D model [J]. Journal on Communications, 2019, 40(5): 211-222.
[9]	Xi SUN,Wei-ming ZHANG,Neng-hai YU,Yao WEI. Steganography based on parameters’ disturbance of spatial image transform [J]. Journal on Communications, 2017, 38(10): 166-174.
[10]	Feng XU,Jia-nan LI,Jian-guo SUN. Research of composite safety protection for digital maps [J]. Journal on Communications, 2016, 37(2): 174-179.
[11]	Tao HAN,Xi CHEN,Yue-fei ZHU. Subtractive pixel adjacency matrix based features for steganalysis of spatial color images [J]. Journal on Communications, 2016, 37(2): 158-165.
[12]	Pei-tao YANG,Wei-ming ZHANG,Neng-hai YU. Reducing false positives of steganalysis via classification of image-acquiring sources [J]. Journal on Communications, 2016, 37(12): 165-170.
[13]	Ming-zhu LAI,Li-guo ZHANG,Wei-miao FENG,Yuan-yuan WANG,Yong WANG,Shou-zheng LI. Study on authority watermark of the electronic chart based on the semantics characteristics [J]. Journal on Communications, 2016, 37(11): 137-145.
[14]	Ji-cang LU,Fen-lin LIU,Xiang-yang LUO,Yi ZHANG. Recognition of PQ stego images based on identifiable statistical feature [J]. Journal on Communications, 2015, 36(3): 139-148.
[15]	. Video steganalysis scheme based on weighted undirected graph [J]. Journal on Communications, 2014, 35(Z1): 6-30.