skip to main content
10.1145/3206004.3206012acmconferencesArticle/Chapter ViewAbstractPublication Pagesih-n-mmsecConference Proceedingsconference-collections
short-paper

Adversarial Examples Against Deep Neural Network based Steganalysis

Published: 14 June 2018 Publication History

Abstract

Deep neural network based steganalysis has developed rapidly in recent years, which poses a challenge to the security of steganography. However, there is no steganography method that can effectively resist the neural networks for steganalysis at present. In this paper, we propose a new strategy that constructs enhanced covers against neural networks with the technique of adversarial examples. The enhanced covers and their corresponding stegos are most likely to be judged as covers by the networks. Besides, we use both deep neural network based steganalysis and high-dimensional feature classifiers to evaluate the performance of steganography and propose a new comprehensive security criterion. We also make a tradeoff between the two analysis systems and improve the comprehensive security. The effectiveness of the proposed scheme is verified with the evidence obtained from the experiments on the BOSSbase using the steganography algorithm of WOW and popular steganalyzers with rich models and three state-of-the-art neural networks.

References

[1]
Shumeet Baluja and Ian Fischer . 2017. Adversarial Transformation Networks: Learning to Generate Adversarial Examples. arXiv preprint arXiv:1703.09387 (2017).
[2]
Patrick Bas, Tomávs Filler, and Tomávs Pevnỳ . 2011. " Break Our Steganographic System": The Ins and Outs of Organizing BOSS Information Hiding. Springer, 59--70.
[3]
Tomas Denemark, Vahid Sedighi, Vojtech Holub, Rémi Cogranne, and Jessica Fridrich . 2014. Selection-channel-aware rich model for steganalysis of digital images Information Forensics and Security (WIFS), 2014 IEEE International Workshop on. IEEE, 48--53.
[4]
Jessica Fridrich and Jan Kodovsky . 2012. Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security Vol. 7, 3 (2012), 868--882.
[5]
Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy . 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014).
[6]
Linjie Guo, Jiangqun Ni, Wenkang Su, Chengpei Tang, and Yun-Qing Shi . 2015. Using statistical image model for JPEG steganography: uniform embedding revisited. IEEE Transactions on Information Forensics and Security Vol. 10, 12 (2015), 2669--2680.
[7]
Vojtech Holub and Jessica Fridrich . 2012. Designing steganographic distortion using directional filters Information Forensics and Security (WIFS), 2012 IEEE International Workshop on. IEEE, 234--239.
[8]
Vojtvech Holub, Jessica Fridrich, and Tomávs Denemark . 2014. Universal distortion function for steganography in an arbitrary domain. EURASIP Journal on Information Security Vol. 2014, 1 (2014), 1.
[9]
Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, and Pieter Abbeel . 2017. Adversarial attacks on neural network policies. arXiv preprint arXiv:1702.02284 (2017).
[10]
Jan Kodovskỳ and Jessica Fridrich . 2012. Steganalysis of JPEG images using rich models. In Media Watermarking, Security, and Forensics 2012, Vol. Vol. 8303. International Society for Optics and Photonics, 83030A.
[11]
Jan Kodovsky, Jessica Fridrich, and Vojtvech Holub . 2012. Ensemble classifiers for steganalysis of digital media. IEEE Transactions on Information Forensics and Security Vol. 7, 2 (2012), 432--444.
[12]
Jernej Kos, Ian Fischer, and Dawn Song . 2017. Adversarial examples for generative models. arXiv preprint arXiv:1702.06832 (2017).
[13]
Sarra Kouider, Marc Chaumont, and William Puech . 2013. Adaptive steganography by oracle (ASO). In Multimedia and Expo (ICME), 2013 IEEE International Conference on. IEEE, 1--6.
[14]
Bin Li, Ming Wang, Jiwu Huang, and Xiaolong Li . 2014. A new cost function for spatial image steganography Image Processing (ICIP), 2014 IEEE International Conference on. IEEE, 4206--4210.
[15]
Jiajun Lu, Theerasit Issaranon, and David Forsyth . 2017. Safetynet: Detecting and rejecting adversarial examples robustly. arXiv preprint arXiv:1704.00103 (2017).
[16]
Tomávs Pevnỳ, Tomávs Filler, and Patrick Bas . 2010. Using high-dimensional image models to perform highly undetectable steganography. In International Workshop on Information Hiding. Springer, 161--177.
[17]
Yinlong Qian, Jing Dong, Wei Wang, and Tieniu Tan . 2015. Deep learning for steganalysis via convolutional neural networks. Media Watermarking, Security, and Forensics Vol. 9409 (2015), 94090J--94090J.
[18]
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus . 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013).
[19]
Weixuan Tang, Haodong Li, Weiqi Luo, and Jiwu Huang . 2014. Adaptive steganalysis against WOW embedding algorithm Proceedings of the 2nd ACM workshop on Information hiding and multimedia security. ACM, 91--96.
[20]
Songtao Wu, Shenghua Zhong, and Yan Liu . 2017 a. Deep residual learning for image steganalysis. Multimedia Tools and Applications (2017), 1--17.
[21]
Songtao Wu, Sheng-Hua Zhong, and Yan Liu . 2016. Steganalysis via Deep Residual Network. In Parallel and Distributed Systems (ICPADS), 2016 IEEE 22nd International Conference on. IEEE, 1233--1236.
[22]
Songtao Wu, Sheng-hua Zhong, and Yan Liu . 2017 b. Residual convolution network based steganalysis with adaptive content suppression Multimedia and Expo (ICME), 2017 IEEE International Conference on. IEEE, 241--246.
[23]
Guanshuo Xu, Han-Zhou Wu, and Yun-Qing Shi . 2016. Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters Vol. 23, 5 (2016), 708--712.
[24]
Jian Ye, Jiangqun Ni, and Yang Yi . 2017. Deep learning hierarchical representations for image steganalysis. IEEE Transactions on Information Forensics and Security Vol. 12, 11 (2017), 2545--2557.

Cited By

View all
  • (2025)ASIGM: An Innovative Adversarial Stego Image Generation Method for Fooling Convolutional Neural Network-Based Image Steganalysis ModelsElectronics10.3390/electronics1404076414:4(764)Online publication date: 15-Feb-2025
  • (2024)High-security image steganography with the combination of multiple competition and channel attentionJournal of Image and Graphics10.11834/jig.23013429:2(355-368)Online publication date: 2024
  • (2024)An image steganography algorithm without data embedding based on style transfer and zero-watermarkingThird International Symposium on Computer Applications and Information Systems (ISCAIS 2024)10.1117/12.3035046(128)Online publication date: 11-Jul-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
IH&MMSec '18: Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security
June 2018
152 pages
ISBN:9781450356251
DOI:10.1145/3206004
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: 14 June 2018

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. adversarial examples
  2. deep neural network
  3. security
  4. steganalysis
  5. steganography

Qualifiers

  • Short-paper

Funding Sources

  • Natural Science Foundation of China

Conference

IH&MMSec '18
Sponsor:

Acceptance Rates

IH&MMSec '18 Paper Acceptance Rate 18 of 40 submissions, 45%;
Overall Acceptance Rate 128 of 318 submissions, 40%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)58
  • Downloads (Last 6 weeks)16
Reflects downloads up to 15 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)ASIGM: An Innovative Adversarial Stego Image Generation Method for Fooling Convolutional Neural Network-Based Image Steganalysis ModelsElectronics10.3390/electronics1404076414:4(764)Online publication date: 15-Feb-2025
  • (2024)High-security image steganography with the combination of multiple competition and channel attentionJournal of Image and Graphics10.11834/jig.23013429:2(355-368)Online publication date: 2024
  • (2024)An image steganography algorithm without data embedding based on style transfer and zero-watermarkingThird International Symposium on Computer Applications and Information Systems (ISCAIS 2024)10.1117/12.3035046(128)Online publication date: 11-Jul-2024
  • (2024)Enhancing steganography capacity through multi-stage generator model in generative adversarial network based image concealmentJournal of Electronic Imaging10.1117/1.JEI.33.3.03302633:03Online publication date: 1-May-2024
  • (2024)ARES: On Adversarial Robustness Enhancement for Image Steganographic Cost LearningIEEE Transactions on Multimedia10.1109/TMM.2024.335354326(6542-6553)Online publication date: 2024
  • (2024)Constructing an Intrinsically Robust Steganalyzer via Learning Neighboring Feature Relationships and Self-Adversarial AdjustmentIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.347065119(9390-9405)Online publication date: 2024
  • (2024)Natias: Neuron Attribution-Based Transferable Image Adversarial SteganographyIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.342189319(6636-6649)Online publication date: 1-Jan-2024
  • (2024)From Cover to Immucover: Adversarial Steganography via Immunized Cover ConstructionIEEE Transactions on Fuzzy Systems10.1109/TFUZZ.2023.332174032:3(1233-1247)Online publication date: Mar-2024
  • (2024)Constructing Immune-Cover for Improving Holistic Security of Spatial Adaptive SteganographyIEEE Transactions on Dependable and Secure Computing10.1109/TDSC.2024.337681521:6(5403-5419)Online publication date: Nov-2024
  • (2024)A High-Performance Image Steganography Scheme Based on Dual-Adversarial NetworksIEEE Signal Processing Letters10.1109/LSP.2024.344017631(2655-2659)Online publication date: 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