A Binary Relevance Adaptive Model-Selection for Ensemble Steganalysis

Abazar, Mahdieh; Masjedi, Peyman; Taheri, Mohammad

doi:10.22042/isecure.2021.262990.596

A Binary Relevance Adaptive Model-Selection for Ensemble Steganalysis

Document Type : Research Article

Authors

Mahdieh Abazar

Peyman Masjedi

Mohammad Taheri

Computer Science and Engineering and Information Technology Department, Shiraz University, Shiraz, Iran.

https://doi.org/10.22042/isecure.2021.262990.596

Abstract

Steganalysis is an interesting classification problem to discriminate the images, including hidden messages from the clean ones. There are many methods, including deep CNN networks, to extract fine features for this classification task. Also, some researches have been conducted to improve the final classifier. Some state-of-the-art methods use ensemble of networks by a voting strategy to achieve more stable performance. In this paper, a selection phase is proposed to filter improper networks before any voting. This filtering is done by a binary relevance multi-label classification approach. Xu-Net and ResT-Net, the most famous state-of-the-art Steganalysis ensemble models, are considered as the base networks for feature extraction. The Logistic Regression (LR) is chosen here as the last layer of the networks for classification. One large-margin Fisher's linear discriminant (FLD) classifier is trained for each one of the networks to measure its suitability in classifying the query image. The proposed method with different approaches is applied on the BOSSbase dataset and compared to traditional voting and some state-of-the-art related ensemble techniques. The results show significant accuracy improvement of the proposed method in comparison with others.

Keywords

Binary Relevance

Ensemble

FLD

Model-Selection

Steganalysis

20.1001.1.20082045.2022.14.1.8.8

[1] Jian Ye, Jiangqun Ni, and Yang Yi. Deep learning hierarchical representations for image steganalysis. IEEE Transactions on Information Forensics and Security, 12(11):25452557, 2017.
[2] Jessica Fridrich and Jan Kodovsky. Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 7(3):868882, 2012.
[3] Tomas Denemark, Vahid Sedighi, Vojtech Holub, Remi Cogranne, and Jessica Fridrich. Selectionchannel-aware rich model for steganalysis of digital images. 2014 IEEE International Workshop on Information Forensics and Security (WIFS), 2014.
[4] Jan Kodovsky, Jessica Fridrich, and Vojtch Holub. Ensemble classifiers for steganalysis of digital media. IEEE Transactions on Information Forensics and Security, 7(2):432444, 2012.
[5] Tabares-Soto Reinel, Ramos-Pollan Raul, and Isaza Gustavo. Deep learning applied to steganalysis of digital images: A systematic review. IEEE Access, 7:6897068990, 2019.
[6] Guanshuo Xu, Han-Zhou Wu, and Yun-Qing Shi. Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters, 23(5):708712, 2016.
[7] Guanshuo Xu, Han-Zhou Wu, and Yun Q.. Shi. Ensemble of cnns for steganalysis. Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security, 2016.
[8] Bin Li, Weihang Wei, Anselmo Ferreira, and Shunquan Tan. Rest-net: Diverse activation modules and parallel subnets-based cnn for spatial image steganalysis. IEEE Signal Processing Letters, 25(5):650654, 2018.
[9] Tayebe Abazar, Peyman Masjedi, and Mohammad Taheri. An efficient ensemble of convolutional deep steganalysis based on clustering. 2020 6th International Conference on Web Research (ICWR), 2020.
[10] Shunquan Tan and Bin Li. Stacked convolutional auto-encoders for steganalysis of digital images. Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific, 2014.
[11] Yinlong Qian, Jing Dong, Wei Wang, and Tieniu Tan. Deep learning for steganalysis via convolutional neural networks. Media Watermarking, Security, and Forensics 2015, 2015.
[12] Yinlong Qian, Jing Dong, Wei Wang, and Tieniu Tan. Learning and transferring representations for image steganalysis using convolutional neural network. 2016 IEEE International Conference on Image Processing (ICIP), 2016.
[13] Mehdi Yedroudj, Frederic Comby, and Marc Chaumont. Yedroudj-net: An efficient cnn for spatial steganalysis. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.
[14] Songtao Wu, Shenghua Zhong, and Yan Liu. Deep residual learning for image steganalysis. Multimedia Tools and Applications, 77(9):1043710453, 2017.
[15] Songtao Wu, Sheng-Hua Zhong, and Yan Liu. Residual convolution network based steganalysis with adaptive content suppression. 2017 IEEE International Conference on Multimedia and Expo (ICME), 2017.
[16] Jian Ye, Jiangqun Ni, and Yang Yi. Deep learning hierarchical representations for image steganalysis. IEEE Transactions on Information Forensics and Security, 12(11):25452557, 2017.
[17] Mehdi Boroumand, Mo Chen, and Jessica Fridrich. Deep residual network for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 14(5):11811193, 2019.
[18] Patrick Bas, Tom Filler, and Tom Pevn. break our steganographic system: The ins and outs of organizing boss. Information Hiding Lecture Notes in Computer Science, page 5970, 2011.
[19] Vojtch Holub, Jessica Fridrich, and Tom Denemark. Universal distortion function for steganography in an arbitrary domain. EURASIP Journal on Information Security, 2014(1), 2014.
[20] Bin Li, Ming Wang, Jiwu Huang, and Xiaolong Li. A new cost function for spatial image steganography. 2014 IEEE International Conference on Image Processing (ICIP), 2014.
[21] Jian Wu, Shiquan Zhao, Victor S. Sheng, Jing Zhang, Chen Ye, Pengpeng Zhao, and Zhiming Cui. Weak-labeled active learning with conditional label dependence for multilabel image classification. IEEE Transactions on Multimedia, 19(6):11561169, 2017.