Page 291 - 《软件学报》2021年第9期

沈军 等:基于卷积神经网络的低嵌入率空域隐写分析 2915

[18] Xu G, Wu HZ, Shi YQ. Ensemble of CNNs for steganalysis: An empirical study. In: Proc. of the ACM Workshop on Information
Hiding and Multimedia Security. ACM, 2016. 103−107.
[19] Yedroudj M, Comby F, Chaumont M. Yedroudj-net: An efficient CNN for spatial steganalysis. In: Proc. of the IEEE Int’l Conf. on
Acoustics, Speech and Signal Processing. IEEE, 2018. 2092−2096.
[20] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc. of the Computer Vision and Pattern
Recognition. Las Vegas: IEEE, 2016. 770−778.
[21] Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proc. of the
Int’l Conf. on Machine Learning. IMLS, 2015. 448−456.
[22] Ye J, Ni J, Yi Y. Deep learning hierarchical representations for image steganalysis. IEEE Trans. on Information Forensics and
Security, 2017,12(11):2545−2557.
[23] Wu S, Zhong S, Liu Y. Deep residual learning for image steganalysis. Multimedia tools and applications, 2018,77(9):10437−10453.
[24] Tsang CF, Fridrich J. Steganalyzing images of arbitrary size with CNNs. Electronic Imaging, 2018,2018(7):1−8.
[25] Shen J. Research on image steganalysis with low embedding rate based on convolutional neural network [MS. Thesis]. Changsha:
Hunan University, 2020 (in Chinese with English abstract).
[26] Chen M, Sedighi V, Boroumand M, Fridrich J. JPEG-phase-aware convolutional neural network for steganalysis of JPEG images.
In: Proc. of the ACM Workshop on Information Hiding and Multimedia Security. Denver: ACM, 2017. 75−84.
[27] Bas P, Filler T, Pevný T. “Break our steganographic system”: The ins and outs of organizing BOSS. In: Proc. of the Int’l Workshop
on Information Hiding. Berlin: Springer-Verlag, 2011. 59−70.
[28] Jia Y, Shelhamer E, Donahue J, Karayev S. Caffe: Convolutional architecture for fast feature embedding. In: Proc. of the ACM
Int’l Conf. on Multimedia. Glasgow: ACM, 2014. 675−678.
[29] Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proc. of the Int’l Conf. on
Artificial Intelligence and Statistics. 2010. 249−256.

附中文参考文献:
[1] 黄炜,赵险峰,冯登国,盛任农.基于主成分分析进行特征融合的 JPEG 隐写分析.软件学报,2012,23(7):1869−1879. http://www.jos.
org.cn/1000-9825/4107.htm [10.3724/SP.J.1001.2012.04107]
[2] 张逸为,张卫明,俞能海.针对特定测试样本的隐写分析方法.软件学报,2018,29(4):987−1001. http://www.jos.org.cn/1000-9825/
5411.htm [doi: 10.13328/j.cnki.jos.005411]
[3] 黄殿中,张静飞,张茹,李鹏超,郭云彪.基于大数据环境的多模态信息隐藏新体系.电子学报,2017,45(2):477−484.
[4] 汤光明,孙艺,徐潇雨,王宇.动态更新失真代价的自适应 JPEG 隐写算法.通信学报,2017,38(9):1−8.
[9] 翟黎明,嘉炬,任魏翔,徐一波,王丽娜.深度学习在图像隐写术与隐写分析领域中的研究进展.信息安全学报,2018,3(6):2−12.
[13] 高培贤,魏立线,刘佳,刘明明.基于卷积神经网络的图像隐写分析方法.计算机应用研究,2019,36(1):54−288.
[25] 沈军.基于卷积神经网络的低嵌入率图像隐写分析研究[硕士学位论文].长沙:湖南大学,2020.

沈军(1993－),男,硕士,主要研究领域为多 秦拯 (1969－ ), 男 ,博士 ,教授 , 博 士生导
媒体信息安全. 师,CCF 专业会员,主要研究领域为数据安
全与隐私保护,云计算,大数据,机器学习.

廖鑫(1985－),男,博士,副教授,博士生导 刘绪崇(1974－),男,博士,教授,主要研究
师,CCF 高级会员,主要研究领域为多媒体 领域为信息网络安全,网络犯罪侦查,人工
安全,人工智能安全,数字取证,密码学. 智能.