| 311 | 0 | 17 |
| 下载次数 | 被引频次 | 阅读次数 |
针对现有的图像隐写分析方法易出现高偏差的问题,构建了一种集成GoogleNet(EGN)模型,用于图像隐写分析。该模型以GoogleNet为基础模型,采用变异的方法生成多个变异体网络,并利用集成学习思想将这些神经网络模型集成在一起,进行图像隐写分析。研究表明,该模型与现有的图像隐写分析方法和单一的GoogleNet相比,有效提高了图像隐写分析检测的准确率,对嵌入率为0.4 bpp的S-UNIWARD嵌入算法的图像隐写分析检测准确率达到96.18%。
Abstract：Existing image steganography analysis methods are prone to high bias. In order to fix the problem,an inte-grated GoogleNet( EGN) model is established to perform image steganalysis. The model uses GoogleNet as the base model and employs a variant approach to generate multiple variant networks,and uses integrated learning ideas to integrate these neural network models together for image steganalysis. The experimental results show that compared with the existing image steganalysis method and the single GoogleNet,the proposed model effectively improves the accuracy of image steganalysis and detection,and the accuracy of image steganalysis and detection of S-UNIWARD embedding algorithm with embedding ratio of 0.4 bpp reaches 96.18%.
[1] CHEDDAD A,CONDELL J,CURRAN K,et al. Digital image steganography:survey and analysis of current methods[J]. Signal Processing,2010,90(3):727-752.
[2] CUI Q,ZHOU Z L,FU Z J,et al. Image steganography based on foreground object generation by generative adversarial networks in mobile edge computing with Internet of Things[J]. IEEE Access,2019,7:90815-90824.
[3] HU D H,WANG L,JIANG W J,et al. A novel image steganography method via deep convolutional generative adversarial networks[J]. IEEE Access,2018,6:38303-38314.
[4] ZOU Y,ZHANG G,LIU L A. Research on image steganography analysis based on deep learning[J]. Journal of Visual Communication and Image Representation,2019,60:266-275.
[5] CUI W X,LIU S H,JIANG F,et al. Multi-stage residual hiding for image-into-audio steganography[C]//ICASSP2020—2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP). Barcelona:IEEE,2020:2832-2836.
[6]郭继昌，何艳红，魏慧文.利用模块化残差网络的图像隐写分析[J].西安电子科技大学学报，2019,46(1):79-85.
[7] COUCHOT J F,COUTURIER R,SALOMON M. Improving blind steganalysis in spatial domain using a criterion to choose the appropriate steganalyzer between CNN and SRM+EC[C]//ICT Systems Security and Privacy Protection,Hamburg:Springer,2017:431-446.
[8] 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.
[9] QIAN Y L,DONG J,WANG W,et al. Deep learning for steganalysis via convolutional neural networks[C]//Media Watermarking,Security,and Forensics 2015. San Francisco:SPIE,2015:9409:94090J-94090J-10.
[10] XU G S,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]魏立线，高培贤，刘佳，等.基于卷积神经网络的图像隐写分析方法[J].计算机应用研究，2019,36(1):235-238.
[12] SZEGEDY C,LIU W,JIA Y Q,et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Boston:IEEE,2015:1-9.
[13] FRIEDMAN J H. Greedy function approximation:a gradient boosting machine[J]. Annals of Statistics,2001,29(5):1189-1232.
[14] ISLAM R,SHAHJALAL M A. Predicting DRC violations using ensemble random forest algorithm[C]//Proceedings of the 56th Annual Design Automation Conference 2019. Las Vegas:ACM,2019:233-236.
[15]CHEN T Q,GUESTRIN C. XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco:ACM,2016:785–794.
[16] KODOVSKY J,FRIDRICH J,HOLUB V. Ensemble classifiers for steganalysis of digital media[J]. IEEE Transactions on Information Forensics and Security,2012,7(2):432-444.
[17] MARVEL L M,BONCELET C G,RETTER C T. Spread spectrum image steganography[J]. IEEE Transactions on Image Processing,1999,8(8):1075-1083.
[18] WANG Z H,GAO N,WANG X,et al. HidingGAN:high capacity information hiding with generative adversarial network[J]. Computer Graphics Forum,2019,38(7):393-401.
[19]VOJTECH H,JESSICA F. Phase-aware projection model for steganalysis of JPEG images[C]//Media Watermarking,Security,and Forensics 2015. Washington D.C.:International Society for Optics and Photonics,2015:94090.
[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]汪然，牛少彰，平西建，等.降低特征类内离散度的JPEG图像隐写分析[J].应用科学学报，2019,37(1):41-50.
[22] CHEN Y H,CAO Y,HU H,et al. Memory enhanced global-local aggregation for video object detection[C]//2020IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Seattle:IEEE,2020:10334-10343.
[23]高培贤，魏立线，刘佳，等.针对图像隐写分析的卷积神经网络结构改进[J].计算机工程，2018,44(10):309-313.
[24]黄思远，张敏情，柯彦，等.基于自注意力机制的图像隐写分析方法[J].计算机应用研究，2021,38(4):1190-1194.
[25]REINEL T S,BRAYAN A A H,ALEJANDRO B O M,et al.GBRAS-net:a convolutional neural network architecture for spatial image steganalysis[J]. IEEE Access,2021,9:14340-14350.
[26]YANG J H,LU B L,XIAO L,et al. Reinforcement learning aided network architecture generation for JPEG image steganalysis[C]//Proceedings of the 2020 ACM Workshop on Information Hiding and Multimedia Security. Denver:ACM,2020:23-32.
[27]KIM J,PARK H,PARK J I. CNN-based image steganalysis using additional data embedding[J]. Multimedia Tools and Applications,2020,79(1/2):1355-1372.
[28]HU Q,MA L,XIE X F,et al. DeepMutation++:a mutation testing framework for deep learning systems[C]//2019 34th IEEE/ACM International Conference on Automated Software Engineering(ASE). San Diego:IEEE,2019:1158-1161.
[29] MA L,ZHANG F Y,SUN J Y,et al. DeepMutation:mutation testing of deep learning systems[C]//2018 IEEE29th International Symposium on Software Reliability Engineering(ISSRE). Memphis:IEEE,2018:100-111.
基本信息:
DOI：10.19573/j.issn2095-0926.202103006
中图分类号:TP391.41;TP309
引用信息:
[1]彭芙蓉,曹继华,石和平等.基于集成GoogleNet的图像隐写分析方法[J].天津职业技术师范大学学报,2021,31(03):30-36.DOI:10.19573/j.issn2095-0926.202103006.
基金信息:
天津市自然科学基金青年项目（18JCQNJC01500）