skip to main content
10.1145/2909827.2930798acmconferencesArticle/Chapter ViewAbstractPublication Pagesih-n-mmsecConference Proceedingsconference-collections
short-paper

Ensemble of CNNs for Steganalysis: An Empirical Study

Published: 20 June 2016 Publication History

Abstract

There has been growing interest in using convolutional neural networks (CNNs) in the fields of image forensics and steganalysis, and some promising results have been reported recently. These works mainly focus on the architectural design of CNNs, usually, a single CNN model is trained and then tested in experiments. It is known that, neural networks, including CNNs, are suitable to form ensembles. From this perspective, in this paper, we employ CNNs as base learners and test several different ensemble strategies. In our study, at first, a recently proposed CNN architecture is adopted to build a group of CNNs, each of them is trained on a random subsample of the training dataset. The output probabilities, or some intermediate feature representations, of each CNN, are then extracted from the original data and pooled together to form new features ready for the second level of classification. To make best use of the trained CNN models, we manage to partially recover the lost information due to spatial subsampling in the pooling layers when forming feature vectors. Performance of the ensemble methods are evaluated on BOSSbase by detecting S-UNIWARD at 0.4 bpp embedding rate. Results have indicated that both the recovery of the lost information, and learning from intermediate representation in CNNs instead of output probabilities, have led to performance improvement.

References

[1]
Y. Freund, and R. E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comp. Syst. Sciences, 55(1): 119--139, Aug. 1997.
[2]
J. H. Friedman. Greedy function approximation: a gradient boosting machine. Annals Statistics, 29(5): 1189--1232, Oct. 2001.
[3]
L. Breiman. Bagging predictors. Machine Learning, 24(2): 123--140, Aug. 1996.
[4]
L. Breiman. Random forests. Machine learning, 45(1): 5--32, Oct. 2001.
[5]
A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. In: Proc. Adv. Neural Inf. Process. Syst., pages 1097--1105, 2012.
[6]
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-fei. Imagenet large scale visual recognition challenge. Int. J. Comp. Vision, 115(3): 211--252, Apr. 2015.
[7]
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In: Proc. IEEE Conf. Comp. Vision Pattern Recognition, pages 1--9, 2015.
[8]
S. Ioffe, and C. Szegedy. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167, Feb. 2015.
[9]
K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. arXiv:1512.03385, Dec. 2015.
[10]
J. Chen, X. Kang, Y. Liu, and Z. J. Wang. Median filtering forensics based on convolutional neural networks. IEEE Signal Process. Lett., 22(11): 1849--1853, Jun. 2015.
[11]
S. Tan, and B. Li. Stacked convolutional auto-encoders for steganalysis of digital images. In: Proc. APSIPA, pages 1--4, Dec. 2014.
[12]
Y. Qian, J. Dong, W. Wang, and T. Tan. Deep learning for steganalysis via convolutional neural networks. In: Proc. SPIE Electronic Imaging, pages 94090J, Mar. 2015.
[13]
L. Pibre, P. Jérôme, D. Ienco, and M. Chaumont. Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch. In: Proc. SPIE Electronic Imaging, Feb. 2016.
[14]
J. Fridrich, and J. Kodovskỳ. Rich models for steganalysis of digital images. IEEE Inf. Forensics Security, 7(3): 868--882, Jun. 2012.
[15]
G. Xu, H. Wu, and Y. Shi. Structural design of convolutional neural networks for steganalysis. IEEE Signal Process. Lett., 23(5): 708--712, Mar. 2016.
[16]
P. Bas, T. Filler, and T. Pevnỳ. "Break our steganographic system": the ins and outs of organizing BOSS. In: Proc. Inf. Hiding, vol. 6958, pages 59--70, Springer, May 2011.
[17]
J. Kodovskỳ, J. Fridrich, and V. Holub. Ensemble classifiers for steganalysis of digital media. IEEE Trans. Inf. Forensics Security, 7(2): 432--444, Apr. 2012.
[18]
V. Holub, and J. Fridrich. Random projections of residuals for digital image steganalysis. IEEE Trans. Inf. Forensics Security, 8(12): 1996--2006, Dec. 2013.
[19]
T. Denemark, V. Sedighi, V. Holub, R. Cogranne, and J. Fridrich. Selection-channel-aware rich model for steganalysis of digital images. In: Proc. Inf. Forensics Security (WIFS), pages 48--53, Dec. 2014.
[20]
W. Tang, H. Li, W. Luo, and J. Huang. Adaptive steganalysis against WOW embedding algorithm. In: Proc. ACM IH&MMSec, pages 91--96, 2014.
[21]
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: convolutional architecture for fast feature embedding. In: Proc. ACM Int. Conf. Multimed., pages 675--678, 2014.
[22]
V. Holub, J. Fridrich, and T. Denemark. Universal distortion function for steganography in an arbitrary domain. EURASIP J. Inf. Security, 2014(1): 1--13, Dec. 2014.

Cited By

View all

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
IH&MMSec '16: Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security
June 2016
200 pages
ISBN:9781450342902
DOI:10.1145/2909827
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 June 2016

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. convolutional neural networks
  2. deep learning.
  3. forensics
  4. steganalysis

Qualifiers

  • Short-paper

Conference

IH&MMSec '16
Sponsor:

Acceptance Rates

IH&MMSec '16 Paper Acceptance Rate 21 of 61 submissions, 34%;
Overall Acceptance Rate 128 of 318 submissions, 40%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)13
  • Downloads (Last 6 weeks)2
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)Research on image steganography based on a conditional invertible neural networkSignal, Image and Video Processing10.1007/s11760-025-03818-019:3Online publication date: 28-Jan-2025
  • (2025)AI Approaches in Steganalysis ResearchEncyclopedia of Cryptography, Security and Privacy10.1007/978-3-030-71522-9_1633(56-60)Online publication date: 8-Jan-2025
  • (2024)Image Steganalysis using Deep Convolution Neural Networks: A Literature SurveyInternational Journal of Sensors, Wireless Communications and Control10.2174/012210327929637024052907550714:4(247-264)Online publication date: Dec-2024
  • (2024)Image Steganography Approaches and Their Detection Strategies: A SurveyACM Computing Surveys10.1145/369496557:2(1-40)Online publication date: 10-Oct-2024
  • (2024)Dig a Hole and Fill in Sand: Adversary and Hiding Decoupled SteganographyProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681330(10440-10448)Online publication date: 28-Oct-2024
  • (2024)Improving image steganography security via ensemble steganalysis and adversarial perturbation minimizationJournal of Information Security and Applications10.1016/j.jisa.2024.10383585(103835)Online publication date: Sep-2024
  • (2024)Semi-supervised QIM steganalysis with ladder networksJournal of Information Security and Applications10.1016/j.jisa.2024.10383485(103834)Online publication date: Sep-2024
  • (2024)Comprehensive Survey on Image Steganalysis Using Deep LearningArray10.1016/j.array.2024.100353(100353)Online publication date: Jun-2024
  • (2024)Applying Convolutional Neural Networks for Enhanced Digital Image SteganalysisPractical Statistical Learning and Data Science Methods10.1007/978-3-031-72215-8_29(697-718)Online publication date: 28-Dec-2024
  • (2024)Color Image Steganalysis Algorithm Based on Quaternion Convolutional Neural NetworkComputational and Experimental Simulations in Engineering10.1007/978-3-031-68775-4_75(983-998)Online publication date: 21-Aug-2024
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media