article

Feature learning for steganalysis using convolutional neural networks

Authors:

Tieniu TanAuthors Info & Claims

Multimedia Tools and Applications, Volume 77, Issue 15

Pages 19633 - 19657

https://doi.org/10.1007/s11042-017-5326-1

Published: 01 August 2018 Publication History

Abstract

Traditional steganalysis methods usually rely on handcrafted features. However, with the rapid development of advanced steganography, manual design of complex features has become increasingly difficult. In this paper, we propose a new paradigm for steganalysis based on the concept of feature learning. In our method, Convolutional Neural Network (CNN) is used to automatically learn features for steganalysis. To make CNN work better for steganalysis, we incorporate domain knowledge of steganalysis (i.e. enhancing stego noise and exploiting nearby dependencies) when designing the CNN architectures. We further propose to use model combination to boost the performance of CNN based method. Additionally, a cropping strategy is proposed to enable the CNN based model to deal with arbitrary input image sizes. We demonstrate the effectiveness of the proposed method against state-of-the-art spatial domain steganographic algorithms such as HUGO, WOW, S-UNIWARD, MiPOD, and HILL-CMD. To help understand the learned features from CNN, we provide visualizations of the learned filters and feature maps. Finally, we also provide quantitative analysis of the learned features from convolutional layers.

References

[1]

Atawneh S, Almomani A, Al Bazar H, Sumari P, Gupta B (2016) Secure and imperceptible digital image steganographic algorithm based on diamond encoding in dwt domain. Multimed Tools Appl 76(18):18451---18472

Digital Library

[2]

Avcibas I, Memon N, Sankur B (2003) Steganalysis using image quality metrics. IEEE Trans Image Process 12(2):221---229

Digital Library

[3]

Bas P, Filler T, Pevny? T (2011) Break our steganographic system: the ins and outs of organizing boss. In: Information hiding. Springer, Berlin, pp 59---70

[4]

Boureau YL, Ponce J, LeCun Y (2010) A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 111---118

Digital Library

[5]

Browne M, Ghidary SS (2003) Convolutional neural networks for image processing: an application in robot vision. In: AI 2003: advances in artificial intelligence. Springer, Berlin, pp 641---652

[6]

Cancelli G, Doërr G., Cox IJ, Barni M (2008) Detection of±?1 lsb steganography based on the amplitude of histogram local extrema. In: 15Th IEEE international conference on image processing. IEEE, Piscataway, pp 1288---1291

[7]

Chen C, Shi YQ (2008) Jpeg image steganalysis utilizing both intrablock and interblock correlations. In: IEEE International symposium on circuits and systems. IEEE, Piscataway, pp 3029---3032

[8]

Couchot JF, Couturier R, Guyeux C, Salomon M (2016) Steganalysis via a convolutional neural network using large convolution filters for embedding process with same stego key. arXiv:1605.07946

[9]

Denemark T, Sedighi V, Holub V, Cogranne R, Fridrich J (2014) Selection-channel-aware rich model for steganalysis of digital images. In: 2014 IEEE international workshop on information forensics and security (WIFS). IEEE, Piscataway, pp 48---53

[10]

Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensics Secur 7(3):868---882

Digital Library

[11]

Fridrich J, Kodovsky? J, Holub V, Goljan M (2011) Steganalysis of content-adaptive steganography in spatial domain. In: Information hiding. Springer, Berlin, pp 102---117

Digital Library

[12]

Geetha S, Sindhu SSS, Kamaraj N (2009) Blind image steganalysis based on content independent statistical measures maximizing the specificity and sensitivity of the system. Comput Secur 28(7):683--- 697

Digital Library

[13]

Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440---1448

Digital Library

[14]

Goljan M, Fridrich J, Holotyak T (2006) New blind steganalysis and its implications. In: Electronic imaging 2006. International society for optics and photonics, Bellingham, pp 607,201---607,201

[15]

Gul G, Kurugollu F (2011) A new methodology in steganalysis: breaking highly undetectable steganograpy (hugo). In: Information hiding. Springer, Berlin, pp 71---84

Digital Library

[16]

He FY, Chen TS, Zhong SP (2015) A classifier ensemble algorithm based on improved rsm for high dimensional steganalysis. Journal of Information Hiding and Multimedia Signal Processing 6(2):198---210

[17]

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770---778

[18]

Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580

[19]

Holotyak T, Fridrich J, Voloshynovskiy S (2005) Blind statistical steganalysis of additive steganography using wavelet higher order statistics. In: Communications and multimedia security, vol. 3677, pp. 273---274

Digital Library

[20]

Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: The IEEE international workshop on information forensics and security (WIFS), pp 234---239

[21]

Holub V, Fridrich J (2013) Digital image steganography using universal distortion. In: Proceedings of the first ACM workshop on information hiding and multimedia security. ACM, New York, pp 59---68

Digital Library

[22]

Holub V, Fridrich J (2013) Random projections of residuals for digital image steganalysis. IEEE Trans Inf Forensics Secur 8(12):1996---2006

Digital Library

[23]

Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167

Digital Library

[24]

Jarrett K, Kavukcuoglu K, Lecun Y et al. (2009) What is the best multi-stage architecture for object recognition?. In: 2009 IEEE 12Th international conference on computer vision. IEEE, Piscataway, pp 2146---2153

[25]

Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: IEEE Conference on computer vision and pattern recognition, pp 1725---1732

Digital Library

[26]

Ker AD, Böhme R. (2008) Revisiting weighted stego-image steganalysis. In: Electronic imaging 2008. International society for optics and photonics, Bellingham, pp 681,905---681,905

[27]

Kodovsky J, Fridrich J, Holub V (2012) Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Forensics Secur 7:432---444

Digital Library

[28]

Krizhevsky A (2012) cuda-convnet. Http://code.google.com/p/cuda-convnet/

[29]

Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097---1105

Digital Library

[30]

LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278---2324

[31]

Li B, Wang M, Li X, Tan S, Huang J (2015) A strategy of clustering modification directions in spatial image steganography. IEEE Trans Inf Forensics Secur 10(9):1905---1917

Digital Library

[32]

Lin M, Chen Q, Yan S (2013) Network in network. arXiv:1312.4400

[33]

Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, Berlin, pp 21---37

[34]

Lyu S, Farid H (2003) Detecting hidden messages using higher-order statistics and support vector machines. In: Information hiding. Springer, Berlin, pp 340---354

Digital Library

[35]

Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 689---696

Digital Library

[36]

Pevny T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inf Forensics Secur 5(2):215---224

Digital Library

[37]

Pevny? T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. In: Information hiding. Springer, Berlin, pp 161---177

[38]

Pibre L, Pasquet J, Ienco D, Chaumont M (2016) Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch. In: EI: electronic imaging

[39]

Qian Y, Dong J, Wang W, Tan T (2015) Deep learning for steganalysis via convolutional neural networks. In: ISAndamp;t/SPIE electronic imaging, pp 94,090j---94,090j

[40]

Qian Y, Dong J, Wang W, Tan T (2016) Learning and transferring representations for image steganalysis using convolutional neural network. In: 2016 IEEE international conference on Image processing (ICIP). IEEE, Piscataway, pp 2752---2756

[41]

Qian Y, Dong J, Wang W, Tan T (2016) Learning representations for steganalysis from regularized cnn model with auxiliary tasks. In: Proceedings of the 2015 international conference on communications, signal processing, and systems. Springer, Berlin, pp 629---637

[42]

Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91---99

Digital Library

[43]

Sedighi V, Cogranne R, Fridrich J (2016) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inf Forensics Secur 11(2):221---234

Digital Library

[44]

Shi YQ, Chen C, Chen W (2007) A markov process based approach to effective attacking jpeg steganography. In: Information hiding. Springer, Berlin, pp 249---264

Digital Library

[45]

Shi YQ, Sutthiwan P, Chen L (2013) Textural features for steganalysis. In: Information hiding. Springer, Berlin, pp 63---77

Digital Library

[46]

Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

[47]

Tan S, Li B (2014) Stacked convolutional auto-encoders for steganalysis of digital images. In: Signal and information processing association annual summit and conference (APSIPA), 2014 asia-pacific. IEEE, Piscataway, pp 1---4

[48]

Tang W, Li H, Luo W, Huang J (2014) Adaptive steganalysis against wow embedding algorithm. In: Proceedings of the 2nd ACM workshop on information hiding and multimedia security, pp 91--- 96

Digital Library

[49]

Wu S, Zhong SH, Liu Y (2016) Steganalysis via deep residual network. In: 2016 IEEE 22nd international conference on Parallel and distributed systems (ICPADS). IEEE, Piscataway, pp 1233---1236

[50]

Xia Z, Wang X, Sun X, Wang B (2014) Steganalysis of least significant bit matching using multi-order differences. Security and Communication Networks 7 (8):1283---1291

Digital Library

[51]

Xia Z, Wang X, Sun X, Liu Q, Xiong N (2016) Steganalysis of lsb matching using differences between nonadjacent pixels. Multimed Tools Appl 75 (4):1947---1962

Digital Library

[52]

Xu G, Wu HZ, Shi YQ (2016) Ensemble of cnns for steganalysis: an empirical study. In: Proceedings of the 4th ACM workshop on information hiding and multimedia security. ACM, New York, pp 103--- 107

Digital Library

[53]

Xu G, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23(5):708---712

[54]

Xuan G, Shi YQ, Gao J, Zou D, Yang C, Zhang Z, Chai P, Chen C, Chen W (2005) Steganalysis based on multiple features formed by statistical moments of wavelet characteristic functions. In: Information hiding. Springer, Berlin, pp 262---277

Digital Library

[55]

Yuan C, Xia Z, Sun X (2017) Coverless image steganography based on sift and bof. Journal of Internet Technology 18(2):435---442

Cited By

Kombrink MGeradts ZWorring M(2024)Image Steganography Approaches and Their Detection Strategies: A SurveyACM Computing Surveys10.1145/369496557:2(1-40)Online publication date: 10-Oct-2024
https://dl.acm.org/doi/10.1145/3694965
Mandal PMukherjee IPaul GChatterji B(2022)Digital image steganographyInformation Sciences: an International Journal10.1016/j.ins.2022.07.120609:C(1451-1488)Online publication date: 1-Sep-2022
https://dl.acm.org/doi/10.1016/j.ins.2022.07.120
Amrutha EArivazhagan SSylvia Lilly Jebarani W(2022)MixNet: A Robust Mixture of Convolutional Neural Networks as Feature Extractors to Detect Stego Images Created by Content-Adaptive SteganographyNeural Processing Letters10.1007/s11063-021-10661-054:2(853-870)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1007/s11063-021-10661-0
Show More Cited By

Feature learning for steganalysis using convolutional neural networks
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches

Recommendations

LSB steganographic method based on reversible histogram transformation function for resisting statistical steganalysis

Statistical steganalysis schemes detect the existence of secret information embedded by steganography. The x^2-detection and Regular-Singular (RS)-attack methods are two well-known statistical steganalysis schemes used against LSB (least significant bit)...
Steganalysis of YASS
MM&Sec '08: Proceedings of the 10th ACM workshop on Multimedia and security

In this paper, we describe a method for attacking Yet Another Steganographic Scheme (YASS), which is designed to be a very secure JPEG steganographic algorithm. The success of YASS is attributed to its innovation in embedding, i.e., hiding data in ...
Implementation of Least Significant Bit Steganography and statistical steganalysis
CCSEIT '12: Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology

Least Significant Bit (LSB) Steganography is a method for hidden information in such a way that can only be detected by its intended recipient. Steganography in Digital media becomes a challenging discipline, since the Human Auditory System (HAS) is ...

Comments

Information & Contributors

Information

Published In

cover image Multimedia Tools and Applications

Multimedia Tools and Applications Volume 77, Issue 15

August 2018

1362 pages

ISSN:1380-7501

Issue’s Table of Contents

Copyright © Copyright © 2018 Springer Science+Business Media, LLC, part of Springer Nature.

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 01 August 2018

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kombrink MGeradts ZWorring M(2024)Image Steganography Approaches and Their Detection Strategies: A SurveyACM Computing Surveys10.1145/369496557:2(1-40)Online publication date: 10-Oct-2024
https://dl.acm.org/doi/10.1145/3694965
Mandal PMukherjee IPaul GChatterji B(2022)Digital image steganographyInformation Sciences: an International Journal10.1016/j.ins.2022.07.120609:C(1451-1488)Online publication date: 1-Sep-2022
https://dl.acm.org/doi/10.1016/j.ins.2022.07.120
Amrutha EArivazhagan SSylvia Lilly Jebarani W(2022)MixNet: A Robust Mixture of Convolutional Neural Networks as Feature Extractors to Detect Stego Images Created by Content-Adaptive SteganographyNeural Processing Letters10.1007/s11063-021-10661-054:2(853-870)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1007/s11063-021-10661-0
Dehdar AKeshavarz AParhizgar N(2022)Image steganalysis using modified graph clustering based ant colony optimization and Random ForestMultimedia Tools and Applications10.1007/s11042-022-13599-082:5(7401-7418)Online publication date: 22-Aug-2022
https://dl.acm.org/doi/10.1007/s11042-022-13599-0
Miranda JParada D(2022)LSB steganography detection in monochromatic still images using artificial neural networksMultimedia Tools and Applications10.1007/s11042-021-11527-281:1(785-805)Online publication date: 1-Jan-2022
https://dl.acm.org/doi/10.1007/s11042-021-11527-2
Amrutha EArivazhagan SJebarani W(2022)Novel color image steganalysis method based on RGB channel empirical modes to expose stego images with diverse payloadsPattern Analysis & Applications10.1007/s10044-022-01102-226:1(239-253)Online publication date: 9-Sep-2022
https://dl.acm.org/doi/10.1007/s10044-022-01102-2
Arivazhagan SAmrutha ESylvia Lilly Jebarani WVeena S(2021)Hybrid convolutional neural network architecture driven by residual features for steganalysis of spatial steganographic algorithmsNeural Computing and Applications10.1007/s00521-021-05837-733:17(11465-11485)Online publication date: 1-Sep-2021
https://dl.acm.org/doi/10.1007/s00521-021-05837-7
Yang JDong CZhang FLei MBai X(2021)MSCNN: Steganographer Detection Based on Multi-Scale Convolutional Neural NetworksWireless Algorithms, Systems, and Applications10.1007/978-3-030-85928-2_17(215-226)Online publication date: 25-Jun-2021
https://dl.acm.org/doi/10.1007/978-3-030-85928-2_17
Ruan FZhang XZhu DXu ZWan SQi L(2020)Deep learning for real-time image steganalysis: a surveyJournal of Real-Time Image Processing10.1007/s11554-019-00915-517:1(149-160)Online publication date: 1-Feb-2020
https://dl.acm.org/doi/10.1007/s11554-019-00915-5
Zhong SWang YRen TZheng MLiu YWu G(2019)Steganographer Detection via Multi-Scale Embedding Probability EstimationACM Transactions on Multimedia Computing, Communications, and Applications10.1145/335269115:4(1-23)Online publication date: 16-Dec-2019
https://dl.acm.org/doi/10.1145/3352691
Show More Cited By

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents