research-article

Public Access

Improving EfficientNet for JPEG Steganalysis

Authors:

Yassine Yousfi,

Jessica Fridrich, and

Clément Fuji TsangAuthors Info & Claims

IH&MMSec '21: Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security

June 2021

Pages 149 - 157

https://doi.org/10.1145/3437880.3460397

Published: 21 June 2021 Publication History

Abstract

In this paper, we study the EfficientNet family pre-trained on ImageNet when used for steganalysis using transfer learning. We show that certain "surgical modifications" aimed at maintaining the input resolution in EfficientNet architectures significantly boost their performance in JPEG steganalysis, establishing thus new benchmarks. The modified models are evaluated by their detection accuracy, the number of parameters, the memory consumption, and the total floating point operations (FLOPs) on the ALASKA II dataset. We also show that, surprisingly, EfficientNets in their "vanilla form" do not perform as well as the SRNet in BOSSbase+BOWS2. This is because, unlike ALASKA II images, BOSSbase+BOWS2 contains aggressively subsampled images with more complex content. The surgical modifications in EfficientNet remedy this underperformance as well.

Supplementary Material

MP4 File (IHMMSec21-fp10.mp4)

In this talk, we present certain "surgical modifications" of the EfficientNet architecture, which significantly boost their performance in JPEG steganalysis. The modified models are evaluated by their detection accuracy, the number of parameters, the memory consumption, and the total floating point operations (FLOPs) on the ALASKA II dataset. Surprisingly, EfficientNets in their "vanilla form" do not perform as well as the SRNet in BOSSbase+BOWS2. This is because, unlike ALASKA II images, BOSSbase+BOWS2 contains aggressively subsampled images with more complex content. The surgical modifications in EfficientNet remedy this underperformance as well.

Download
314.62 MB

References

[1]

J. Fridrich and J. Kodovský, "Rich models for steganalysis of digital images," IEEE Transactions on Information Forensics and Security, vol. 7, no. 3, pp. 868--882, June 2011.

Digital Library

[2]

J. Kodovský and J. Fridrich, "Steganalysis of JPEG images using rich models," in Proceedings SPIE, Electronic Imaging, Media Watermarking, Security, and Forensics 2012, A. Alattar, N. D. Memon, and E. J. Delp, Eds., vol. 8303, San Francisco, CA, January 23--26, 2012, pp. 0A 1--13.

[3]

L. Chen, Y. Shi, P. Sutthiwan, and X. Niu, "A novel mapping scheme for steganalysis," in International Workshop on Digital Forensics and Watermaking, ser. LNCS, Y. Shi, H.-J. Kim, and F. Perez-Gonzalez, Eds., vol. 7809.hskip 1em plus 0.5em minus 0.4emrelax Springer Berlin Heidelberg, 2013, pp. 19--33.

[4]

W. Tang, H. Li, W. Luo, and J. Huang, "Adaptive steganalysis against WOW embedding algorithm," in 2nd ACM IH&MMSec. Workshop, A. Uhl, S. Katzenbeisser, R. Kwitt, and A. Piva, Eds., Salzburg, Austria, June 11--13, 2014, pp. 91--96.

[5]

T. Denemark, V. Sedighi, V. Holub, R. Cogranne, and J. Fridrich, "Selection-channel-aware rich model for steganalysis of digital images," in IEEE International Workshop on Information Forensics and Security, Atlanta, GA, December 3--5, 2014.

[6]

V. Holub and J. Fridrich, "Phase-aware projection model for steganalysis of JPEG images," in Proceedings SPIE, Electronic Imaging, Media Watermarking, Security, and Forensics 2015, A. Alattar and N. D. Memon, Eds., vol. 9409, San Francisco, CA, February 8--12, 2015.

[7]

X. Song, F. Liu, C. Yang, X. Luo, and Y. Zhang, "Steganalysis of adaptive JPEG steganography using 2D Gabor filters," in 3rd ACM IH&MMSec. Workshop, P. Comesana, J. Fridrich, and A. Alattar, Eds., Portland, Oregon, June 17--19, 2015.

[8]

T. Denemark, M. Boroumand, and J. Fridrich, "Steganalysis features for content-adaptive JPEG steganography," IEEE Transactions on Information Forensics and Security, vol. 11, no. 8, pp. 1736--1746, August 2016.

Digital Library

[9]

Y. Qian, J. Dong, W. Wang, and T. Tan, "Deep learning for steganalysis via convolutional neural networks," in Proceedings SPIE, Electronic Imaging, Media Watermarking, Security, and Forensics 2015, A. Alattar and N. D. Memon, Eds., vol. 9409, San Francisco, CA, February 8--12, 2015.

[10]

G. Xu, H. Z. Wu, and Y. Q. Shi, "Structural design of convolutional neural networks for steganalysis," IEEE Signal Processing Letters, vol. 23, no. 5, pp. 708--712, May 2016.

[11]

J. Ye, J. Ni, and Y. Yi, "Deep learning hierarchical representations for image steganalysis," IEEE Transactions on Information Forensics and Security, vol. 12, no. 11, pp. 2545--2557, November 2017.

Digital Library

[12]

M. Yedroudj, F. Comby, and M. Chaumont, "Yedroudj-net: An efficient CNN for spatial steganalysis," in IEEE ICASSP, Alberta, Canada, April 15--20, 2018, pp. 2092--2096.

[13]

B. Li, W. Wei, A. Ferreira, and S. Tan, "ReST-Net: Diverse activation modules and parallel subnets-based CNN for spatial image steganalysis," IEEE Signal Processing Letters, vol. 25, no. 5, pp. 650--654, May 2018.

[14]

BIBentryALTinterwordspacingJ. Zeng, S. Tan, G. Liu, B. Li, and J. Huang, "WISERNet: Wider separate-then-reunion network for steganalysis of color images," CoRR, vol. abs/1803.04805, 2018. [Online]. Available: http://arxiv.org/abs/1803.04805BIBentrySTDinterwordspacing

[15]

M. Chen, V. Sedighi, M. Boroumand, and J. Fridrich, "JPEG-phase-aware convolutional neural network for steganalysis of JPEG images," in The 5th ACM Workshop on Information Hiding and Multimedia Security, M. Stamm, M. Kirchner, and S. Voloshynovskiy, Eds., Philadelphia, PA, June 20--22, 2017.

[16]

BIBentryALTinterwordspacingJ. Yang, Y.-Q. Shi, E. Wong, and X. Kang, "JPEG steganalysis based on DenseNet," vol. abs/1711.09335, 2017. [Online]. Available: http://arxiv.org/abs/1711.09335BIBentrySTDinterwordspacing

[17]

J. Zeng, S. Tan, B. Li, and J. Huang, "Large-scale JPEG image steganalysis using hybrid deep-learning framework," IEEE Transactions on Information Forensics and Security, vol. 13, no. 5, pp. 1200--1214, May 2018.

Digital Library

[18]

G. Xu, "Deep convolutional neural network to detect J-UNIWARD," in The 5th ACM Workshop on Information Hiding and Multimedia Security, M. Stamm, M. Kirchner, and S. Voloshynovskiy, Eds., Philadelphia, PA, June 20--22, 2017.

[19]

A. Rössler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Niessner, "Faceforensics+: Learning to detect manipulated facial images," in 2019 IEEE/CVF International Conference on Computer Vision, 2019, pp. 1--11.

[20]

F. Marra, D. Gragnaniello, D. Cozzolino, and L. Verdoliva, "Detection of GAN-generated fake images over social networks," in 2018 IEEE Conference on Multimedia Information Processing and Retrieval, 2018, pp. 384--389.

[21]

D. Cozzolino, J. Thies, A. Rössler, C. Riess, M. Nießner, and L. Verdoliva, "ForensicTransfer: Weakly-supervised domain adaptation for forgery detection," arXiv, 2018. [Online]. Available: http://arxiv.org/abs/1812.02510

[22]

S. Y. Wang, O. Wang, R. Zhang, A. Owens, and A. A. Efros, "CNN-generated images are surprisingly easy to spot... for now," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8692--8701.

[23]

R. Cogranne, Q. Giboulot, and P. Bas, "ALASKA--2: Challenging academic research on steganalysis with realistic images," in IEEE International Workshop on Information Forensics and Security, Held virtually, December 6--11, 2020.

[24]

Y. Yousfi, J. Butora, E. Khvedchenya, and J. Fridrich, "ImageNet pre-trained CNNs for JPEG steganalysis," in IEEE International Workshop on Information Forensics and Security, Held virtually, December 6--11, 2020.

[25]

K. Chubachi, "An ensemble model using CNNs on different domains for ALASKA2 image steganalysis," in IEEE International Workshop on Information Forensics and Security, Held virtually, December 6--11, 2020.

[26]

G. Xu, "1st place solution," https://www.kaggle.com/c/alaska2-image-steganalysis/discussion/168548, 2020, [Online; accessed 29-December-2020].

[27]

T. Mingxing and V. L. Quoc, "EfficientNet: Rethinking model scaling for convolutional neural networks," in Proceedings of the 36th International Conference on Machine Learning, vol. 97, June 9--15, 2019, pp. 6105--6114.

[28]

J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "ImageNet: A large-scale hierarchical image database," in 2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20--25, 2009, pp. 248--255.

[29]

M. Boroumand, M. Chen, and J. Fridrich, "Deep residual network for steganalysis of digital images," IEEE Transactions on Information Forensics and Security, vol. 14, no. 5, pp. 1181--1193, May 2019.

Digital Library

[30]

S. Han, J. Pool, J. Tran, and W. Dally, "Learning both weights and connections for efficient neural networks," in Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, Eds., vol. 28, 2015.

[31]

S. Tan, W. Wu, Z. Shao, Q. Li, B. Li, and J. Huang, "CALPA-NET: Channel-pruning-assisted deep residual network for steganalysis of digital images," IEEE Transactions on Information Forensics and Security, vol. 16, pp. 131--146, 2021.

[32]

G. Hinton, O. Vinyals, and J. Dean, "Distilling the knowledge in a neural network," arXiv preprint arXiv:1503.02531, 2015.

[33]

V. Holub, J. Fridrich, and T. Denemark, "Universal distortion design for steganography in an arbitrary domain," EURASIP Journal on Information Security, Special Issue on Revised Selected Papers of the 1st ACM IH and MMS Workshop, vol. 2014:1, 2014.

[34]

R. Cogranne, Q. Giboulot, and P. Bas, "Steganography by minimizing statistical detectability: The cases of JPEG and color images," in The 8th ACM Workshop on Information Hiding and Multimedia Security, C. Riess and F. Schirrmacher, Eds.hskip 1em plus 0.5em minus 0.4emrelax Held virtually: ACM Press, 2020.

[35]

L. Guo, J. Ni, and Y. Q. Shi, "Uniform embedding for efficient JPEG steganography," IEEE Transactions on Information Forensics and Security, vol. 9, no. 5, pp. 814--825, May 2014.

Digital Library

[36]

J. Hu, L. Shen, and G. Sun, "Squeeze-and-excitation networks," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132--7141.

[37]

T. Mingxing and V. L. Quoc, "MixConv: Mixed depthwise convolutional kernels," in British Machine Vision Conference, BMVC, September 9--12, 2019.

[38]

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510--4520.

[39]

K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in 2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 27--30, 2016, pp. 770--778.

[40]

Q. Ha, "Single effnet-b0 private LB 0.921: How to modify effnet architecture," https://www.kaggle.com/c/alaska2-image-steganalysis/discussion/168542, 2020, [Online; accessed 29-December-2020].

[41]

P. Bas, T. Filler, and T. Pevný, "Break our steganographic system -- the ins and outs of organizing BOSS," in Information Hiding, 13th International Conference, ser. rmLecture Notes in Computer Science, T. Filler, T. Pevný, A. Ker, and S. Craver, Eds., vol. 6958, Prague, Czech Republic, May 18--20, 2011, pp. 59--70.

[42]

P. Bas and T. Furon, "BOWS-2," http://bows2.ec-lille.fr, July 2007.

[43]

R. Cogranne, "J-MiPOD source code," personal communication, [e-mail; sent 21-December-2020].

[44]

R. Cogranne, V. Sedighi, and J. Fridrich, "Practical strategies for contentadaptive batch steganography and pooled steganalysis," in Proceedings IEEE, International Conference on Acoustics, Speech, and Signal Processing, New Orleans, LA, March 5--9, 2017, pp. 2122--2126.

[45]

R. Cogranne, Q. Giboulot, and P. Bas, "The ALASKA steganalysis challenge: A first step towards steganalysis "Into the wild"," in The 7th ACM Workshop on Information Hiding and Multimedia Security, R. Cogranne and L. Verdoliva, Eds.hskip 1em plus 0.5em minus 0.4emrelax Paris, France: ACM Press, July 3--5, 2019.

Digital Library

[46]

A. D. Ker and R. Böhme, "Revisiting weighted stego-image steganalysis," in Proceedings SPIE, Electronic Imaging, Security, Forensics, Steganography, and Watermarking of Multimedia Contents X, E. J. Delp, P. W. Wong, J. Dittmann, and N. D. Memon, Eds., vol. 6819, San Jose, CA, January 27--31, 2008, pp. 5 1--17.

Cited By

Cui QZhou ZMeng RWang SYan HWu Q(2024)ARES: On Adversarial Robustness Enhancement for Image Steganographic Cost LearningIEEE Transactions on Multimedia10.1109/TMM.2024.335354326(6542-6553)Online publication date: 2024
https://doi.org/10.1109/TMM.2024.3353543
Butora JBas P(2024)Size-Independent Reliable CNN for RJCA SteganalysisIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.337984919(4420-4431)Online publication date: 2024
https://doi.org/10.1109/TIFS.2024.3379849
Gupta AChhikara RSharma P(2024)Embedded Feature Selection Approach Using Penalized Logistic Regression for Universal SteganalysisProcedia Computer Science10.1016/j.procs.2024.04.150235(1590-1599)Online publication date: 2024
https://doi.org/10.1016/j.procs.2024.04.150
Show More Cited By

Index Terms

Improving EfficientNet for JPEG Steganalysis
1. Computing methodologies
  1. Computer graphics
    1. Image manipulation
      1. Image processing
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

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)...
Read More
Steganalysis of YASS

A promising steganographic method--Yet Another Steganography Scheme (YASS)--was designed to resist blind steganalysis via embedding data in randomized locations. In addition to a concrete realization which is named the YASS algorithm in this paper, a ...
Read More
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 ...
Read More

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

IH&MMSec '21: Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security

June 2021

205 pages

ISBN:9781450382953

DOI:10.1145/3437880

General Chairs:
Dirk Borghys
Royal Military Academy, Brussels, Belgium
,
Patrick Bas
CNRS CRISTAL, Lille, France
,
Program Chairs:
Luisa Verdoliva
University Federico II of Naples, Italy
,
Tomáš Pevný
Czech Technical University in Prague, Czech Republic
,
Bin Li
Shenzhen University, China
,
Jennifer Newman
Iowa State University, Ames, USA

Copyright © 2021 ACM.

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

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 June 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

NSF (National Science Foundation)

Conference

IH&MMSec '21

Sponsor:

SIGMM

IH&MMSec '21: ACM Workshop on Information Hiding and Multimedia Security

June 22 - 25, 2021

Virtual Event, Belgium

Acceptance Rates

Overall Acceptance Rate 128 of 318 submissions, 40%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

28
Total Citations
View Citations
711
Total Downloads

Downloads (Last 12 months)251
Downloads (Last 6 weeks)28

Other Metrics

View Author Metrics

Citations

Cited By

Cui QZhou ZMeng RWang SYan HWu Q(2024)ARES: On Adversarial Robustness Enhancement for Image Steganographic Cost LearningIEEE Transactions on Multimedia10.1109/TMM.2024.335354326(6542-6553)Online publication date: 2024
https://doi.org/10.1109/TMM.2024.3353543
Butora JBas P(2024)Size-Independent Reliable CNN for RJCA SteganalysisIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.337984919(4420-4431)Online publication date: 2024
https://doi.org/10.1109/TIFS.2024.3379849
Gupta AChhikara RSharma P(2024)Embedded Feature Selection Approach Using Penalized Logistic Regression for Universal SteganalysisProcedia Computer Science10.1016/j.procs.2024.04.150235(1590-1599)Online publication date: 2024
https://doi.org/10.1016/j.procs.2024.04.150
Hussain ITan SHuang J(2024)A semi-supervised deep learning approach for cropped image detectionExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.122832243:COnline publication date: 25-Jun-2024
https://dl.acm.org/doi/10.1016/j.eswa.2023.122832
Gupta AChhikara RSharma P(2024)CIRNet: An Improved Lightweight Convolution Neural Network Architecture with Inverted Residuals for Universal SteganalysisArabian Journal for Science and Engineering10.1007/s13369-023-08630-xOnline publication date: 17-Jan-2024
https://doi.org/10.1007/s13369-023-08630-x
Gupta AChhikara RSharma P(2024)A Comparative Analysis of Different CNN Models for Spatial Domain SteganalysisDeep Learning Techniques for Automation and Industrial Applications10.1002/9781394234271.ch8(109-127)Online publication date: 21-Jun-2024
https://doi.org/10.1002/9781394234271.ch8
Li HWang JXiong NZhang YVasilakos ALuo X(2023)A Siamese Inverted Residuals Network Image Steganalysis Scheme based on Deep LearningACM Transactions on Multimedia Computing, Communications, and Applications10.1145/357916619:6(1-23)Online publication date: 12-Jul-2023
https://dl.acm.org/doi/10.1145/3579166
Beneš MLorch BBöhme R(2023)JPEG Steganalysis Using Leaked Cover Thumbnails2023 IEEE International Workshop on Information Forensics and Security (WIFS)10.1109/WIFS58808.2023.10374587(1-6)Online publication date: 4-Dec-2023
https://doi.org/10.1109/WIFS58808.2023.10374587
Giboulot QPevný TKer A(2023)The Non-Zero-Sum Game of Steganography in Heterogeneous EnvironmentsIEEE Transactions on Information Forensics and Security10.1109/TIFS.2023.329594518(4436-4448)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1109/TIFS.2023.3295945
Butora JBas P(2023)Side-Informed Steganography for JPEG Images by Modeling Decompressed ImagesIEEE Transactions on Information Forensics and Security10.1109/TIFS.2023.326888418(2683-2695)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1109/TIFS.2023.3268884
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents