Abstract
Image steganography refers to embedding secret information into a cover image without drawing perceptible distortions. Nevertheless, steganalyzers are potentially reveal steganography by detecting subtle modifications, especially with the introduction of deep learning into image steganalysis. Recent researches show that adversarial examples can greatly enhance the security of image steganography works. In this work, a new terminology of Universal Adversarial Perturbations (UAPs) is presented to further improve the security of image steganography. Specifically, we introduce a generator within the framework of generative adversarial networks (GAN) that learns to generate UAPs, where the UAPs can be applied to universal images without the need to design perturbation specific to an individual image. The UAPs are directly added to the embedding probability map of the image, which can make the generated stego image more deceptive. Experimental results show that the proposed UAPs can effectively improve the security of image steganography.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Bender W, Gruhl D, Morimoto N et al (1996) Techniques for data hiding. IBM Syst J 35(3.4):313–336
Pevný T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. Berlin, Heidelberg, International Workshop on Information Hiding. Springer, pp 161–177
Pevny T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inf Forensics Secur 5(2):215–224
Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. IEEE international workshop on information forensics and security (WIFS). IEEE, pp 234-239
Holub V, Fridrich J (2013) Digital image steganography using universal distortion. Proceedings of the first ACM workshop on information hiding and multimedia security, pp 59-68
Li B, Wang M, Huang J et al (2014) A new cost function for spatial image steganography. IEEE international conference on image processing (ICIP). IEEE, pp 4206-4210
Holub V, Fridrich J, Denemark T (2014) Universal distortion function for steganography in an arbitrary domain. EURASIP J Inf Secur 2014(1):1–13
Guo L, Ni J, Shi YQ (2014) Uniform embedding for efficient JPEG steganography. IEEE Trans Inf Forensics Secur 9(5):814–825
Guo L, Ni J, Su W et al (2015) Using statistical image model for JPEG steganography: Uniform embedding revisited. IEEE Trans Inf Forensics Secur 10(12):2669–2680
Farid H (2001) Detecting steganographic messages in digital images
Fan RE, Chang KW, Hsieh CJ et al (2008) LIBLINEAR: A library for large linear classification. J Mach Learn Res 9:1871–1874
Kodovský J, Fridrich J (2011) Steganalysis in high dimensions: Fusing classifiers built on random subspaces. Media watermarking, security, and forensics III. SPIE, 7880, pp 204-216
Kodovsky J, Fridrich J, Holub V (2011) Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Forensics Secur 7(2):432–444
Xu G, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23(5):708–712
Deng X, Chen B, Luo W et al (2019) Fast and effective global covariance pooling network for image steganalysis. Proceedings of the ACM workshop on information hiding and multimedia security, pp 230-234
Boroumand M, Chen M, Fridrich J (2018) Deep residual network for steganalysis of digital images. IEEE Trans Inf Forensics Secur 14(5):1181–1193
Szegedy C, Zaremba W, Sutskever I et al (2013) Intriguing properties of neural networks. Preprint arXiv:1312.6199
Nguyen A, Yosinski J, Clune J (2015) Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 427-436
Zhang Y, Zhang W, Chen K et al (2018) Adversarial examples against deep neural network based steganalysis. Proceedings of the 6th ACM workshop on information hiding and multimedia security, pp 67–72
Tang W, Li B, Tan S et al (2019) CNN-based adversarial embedding for image steganography. IEEE Trans Inf Forensics Secur 14(8):2074–2087
Bernard S, Bas P, Klein J et al (2020) Explicit optimization of min max steganographic game. IEEE Trans Inf Forensics Secur 16:812–823
Mo H, Song T, Chen B et al (2019) Enhancing JPEG, steganography using iterative adversarial examples. 2019 IEEE international workshop on information forensics and security (WIFS). IEEE, pp 1–6
Liu M, Luo W, Zheng P et al (2021) A New Adversarial Embedding Method for Enhancing Image Steganography. IEEE Trans Inf Forensics Secur 16:4621–4634
Moosavi-Dezfooli SM, Fawzi A, Fawzi O et al (2017) Universal adversarial perturbations. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1765-1773
Goodfellow I J, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. Preprint arXiv:1412.6572
Huang S, Papernot N, Goodfellow I et al (2017) Adversarial attacks on neural network policies. Preprint arXiv:1702.02284
Baluja S, Fischer I (2018) Learning to attack: adversarial transformation networks. Thirty-second aaai conference on artificial intelligence
Goodfellow IJ, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial networks. Adv Neural Inf Process Syst 3:2672–2680
Hayes J, Danezis G (2018) Learning universal adversarial perturbations with generative models. 2018 IEEE security and privacy workshops (SPW). IEEE, pp 43–49
Filler T, Judas J, Fridrich J (2011) Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans Inf Forensics Secur 6(3):920–935
Sedighi V, Cogranne R, Fridrich J (2015) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inf Forensics Secur 11(2):221–234
Fridrich J, Filler T (2007) Practical methods for minimizing embedding impact in steganography. Security, Steganography, and Watermarking of Multimedia Contents IX. SPIE, 6505, pp 13-27
Yang J, Ruan D, Huang J et al (2019) An embedding cost learning framework using GAN. IEEE Trans Inf Forensics Secur 15:839–851
Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. IEEE symposium on security and privacy (sp). IEEE, pp 39–57
Chen PY, Zhang H, Sharma Y et al (2017) Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models. Proceedings of the 10th ACM workshop on artificial intelligence and security, pp 15-26
Bas P, Filler T, Pevnỳ T (2011) “Break our steganographic system”: the ins and outs of organizing BOSS. Berlin, Heidelberg, International workshop on information hiding. Springer, pp 59–70
Bas P, Furon T (2007) BOWS-2. [Online]. Available: http://bows2.ec-lille.fr
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China (61972143, 61972142).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, L., Liu, X., Wang, D. et al. Enhancing image steganography security via universal adversarial perturbations. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-19122-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-024-19122-x