Image Steganography Location Research Based on Pixel Probability Prediction

doi:10.3778/j.issn.1002-8331.2101-0422

Abstract

Abstract: In order to further enhance the practicability of image steganalysis, this paper expands the research goal of image steganalysis as steganography location of adaptive steganography and non-adaptive steganography LSB matching, an end-to-end steganography localization network PSL_NET is proposed. Input an image at the input end, and locate the position of the steganographic pixel of the image at the output end. In the preprocessing layer, the high-pass filter of the spatial rich model is used to extract the residual noise images. In the depth residual layer, deep residual learning is used to enhance the expression ability of steganographic features. In the pixel prediction layer, using the mask image which marks the actual position of the steganographic pixel to perform supervised learning, as well as treating the pixels in the smooth or texture area without distinction, the probability whether each pixel is steganographic pixels is predicted, and finally predict the steganographic pixels of the input image. The imbalance problem of positive and negative samples are solved from the perspective of objective function to improve the detection accuracy. In the experiment based on BOSSbase v1.01, when the network predicts the steganographic image of the adaptive steganography algorithm S-UNIWARD at the payload of 0.4 BPP, the pixel detection accuracy is 0.981 74, and the experiments also verify the network can detect the steganographic image embedded by non-content adaptive steganography LSB matching.

Key words: image steganalysis, content adaptive steganography, LSB matching, deep learning, steganography location

摘要： 为进一步增强图像隐写分析的实用性，对内容自适应隐写术和非内容自适应LSB matching的隐写像素定位问题展开研究，提出一种端到端的图像隐写定位网络PSL_NET，在输入端输入一张图像，输出端定位出图像的隐写像素的位置。在预处理层中，利用空域富模型的高通滤波器提取残噪图像；在深度残差层中，通过深度残差学习增强隐写特征的表达能力；在像素预测层中，利用标记出隐写像素实际位置的掩码图像进行有监督地学习，增强网络对局部隐写像素的感知能力，无区别对待平滑或者纹理区域的像素，逐一预测图像每位像素是真实位或是隐写位，最终预测出图像的隐写像素位；从目标函数层面解决正负样本的不均衡问题，提升检测精度。在基于BOSSbase v1.01数据源展开的实验中，该网络对经自适应隐写术S-UNIWARD在负载为0.4?BPP嵌入的隐写图像的像素检测准确度为0.981?74，实验验证该网络同时适用于对经非内容自适应隐写术LSB matching嵌入后的隐写图像进行隐写像素定位。

关键词: 图像隐写分析, 内容自适应隐写术, LSB matching, 深度学习, 隐写定位

CHEN Sheng, LI Zhi. Image Steganography Location Research Based on Pixel Probability Prediction[J]. Computer Engineering and Applications, 2022, 58(12): 85-93.

陈升, 李智. 基于逐像素概率预测的图像隐写定位研究[J]. 计算机工程与应用, 2022, 58(12): 85-93.

References

[1] PEVNY T，FILLER T，BAS P.Using high-dimensional image models to perform highly undetectable steganography[J].Lecture Notes in Computer Science，2010，6387：161-177.
[2] HOLUB V，FRIDRICH J.Designing steganographic distortion using directional filters[C]//2012 IEEE International Workshop on Information Forensics and Security（WIFS），2012：234-239.
[3] HOLUB V，FRIDRICH J.Digital image steganography using universal distortion[C]//Proceedings of the First ACM Workshop on Information Hiding and Multimedia Security，2013：59-68.
[4] HOLUB V，FRIDRICH J，DENEMARK T.Universal distortion function for steganography in an arbitrary domain[J].Eurasip Journal on Information Security，2014（1）：1.
[5] FRIDRICH J，KODOVSKY J.Rich models for steganalysis of digital images[J].IEEE Transactions on Information Forensics and Security，2012，7（3）：868-882.
[6] HOLUB V，FRIDRICH V.Random projections of residuals for digital image steganalysis[J].IEEE Transactions on Information Forensics and Security，2013，8（12）：1996.
[7] DENEMARK T，SEDIGHI V，HOLUB V，et al.Selection-channel-aware rich model for steganalysis of digital images[C]//2014 IEEE International Workshop on Information Forensics and Security（WIFS），2014：48-53.
[8] TANG W，LI H，LUO W，et al.Adaptive steganalysis against WOW embedding algorithm[C]//Proceedings of the 2nd ACM Workshop on Information Hiding and Multimedia Security，2014：91-96.
[9] QIAN Y，DONG J，WANG W，et al.Deep learning for steganalysis via convolutional neural networks[C]//Media Watermarking，Security，and Forensics 2015，International Society for Optics and Photonics，2015.
[10] 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.
[11] 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.
[12] 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.
[13] KONG X W，LIU W F，YOU X G.Secret message location steganalysis based on local coherences of hue[C]//Pacific-Rim Conference on Multimedia.Berlin，Heidelberg：Springer，2005：301-311.
[14] KER A D.Locating steganographic payload via WS residuals[C]//Proceedings of the 10th ACM Workshop on Multimedia and Security，2008：27-32.
[15] QUACH T T.Locating payload embedded by group-parity steganography[J].Digital Investigation，2012，9（2）：160-166.
[16] SUN Y，ZHANG H，ZHANG T，et al.Deep neural networks for efficient steganographic payload location[J].Journal of Real-Time Image Processing，2019，16（3）：635-647.
[17] MIELIKAINEN J.LSB matching revisited[J].IEEE Signal Processing Letters，2006，13（5）：285-287.
[18] 柳权祺.自适应隐写术的负载定位研究与分析[D].杭州：杭州电子科技大学，2020.
LIU Q Q.Research and analysis of payload location for content adaptive steganography[D].Hangzhou：Hangzhou University of Electronic Science and Technology，2020.
[19] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016.
[20] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017（99）：2999-3007.
[21] 翟黎明，嘉炬，任魏翔，等.深度学习在图像隐写术与隐写分析领域中的研究进展[J].信息安全学报，2018，3（6）：1-12.
ZHAI L M，JIA J，REN W X，et al.Recent advances in deep learning for image steganography and steganalysis[J].Journal of Cyber Security，2018，3（6）：1-12.