Abstract
Recently, the researchers start to apply adversarial attack to enhance the security of steganographic algorithms. The typical deep learning model is vulnerable to adversarial attack. Such attack is generating special instance via neural network. The generated instance can increase the detection error of the steganalyzer. In this paper, we propose a practical adversarial method to enhance the security of typical distortion-minimizing steganographic algorithms. The proposed method is an adaptation of the Fast Gradient Sign Method in the steganography. We utilize the gradients back-propagated from the deep-learning steganalyzer to control the changing direction of the pixels. This kind of steganaographic modification in the image helps to improve the security towards the steganalysis. The experimental results prove that the proposed method can enhance the security of typical distortion-minimizing steganaographic algorithms.
Similar content being viewed by others
References
Abdulla AA, Jassim SA, Sellahewa H (2013) Efficient high-capacity steganography technique. In: Proc. SPIE Electronic imaging security forensics steganography and watermarking of multimedia contents
Abdulla AA, Sellahewa H, Jassim SA (2019) Improving embedding efficiency for digital steganography by exploiting similarities between secret and cover images. Multimed Tools Appl, 1–25
Boroumand M, Chen M, Fridrich J (2019) Deep residual network for steganalysis of digital images. IEEE Trans Inf Forensic Secur 14(5):1181–1193
Chen M, Sedighi V, Boroumand M (2017) JPEG-phase-aware convolutional neural network for steganalysis of JPEG images. In: Proceedings of the 5th ACM workshop on information hiding and multimedia security. ACM, pp 75–84
Denemark T, Fridrich J (2015) Improving steganographic security by synchronizing the selection channel. In: Proceedings of the 3rd ACM workshop on information hiding and multimedia security. ACM, pp 5–14
Denemark T, Fridrich J (2015) Side-informed steganography with additive distortion. In: 2012 IEEE international workshop on information forensics and security (WIFS). IEEE, pp 1–6
Denemark T, Fridrich J (2017) Steganography with multiple jpeg images of the same scene. IEEE Trans Inf Forensic Secur 12(10):2308–2319
Denemark T, Fridrich J (2017) Steganography with two jpegs of the same scene. In: ICASSP, pp 2117–2121
Filler T, Judas J, Fridrich J (2011) Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans Inf Forensic Secur 6(3):920–935
Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensic Secur 7(3):868–882
Fridrich J, Kodovsky J (2013) Multivariate gaussian model for designing additive distortion for steganography. In: ICASSP, pp 2949–2953
Goodfellow I, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv:1412.6572
Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: 2012 IEEE international workshop on information forensics and security (WIFS). IEEE, pp 234–239
Holub V, Fridrich J, Denemark T (2014) Universal distortion function for steganography in an arbitrary domain. EURASIP J Inf Secur 2014(1):1–13
Li B, Tan S, Wang M, Huang J (2014) Investigation on cost assignment in spatial image steganography. IEEE Trans Inf Forensic Secur 9(8):1264–1277
Li B, Wang M, Huang J, Li X (2014) A new cost function for spatial image steganography. In: 2014 IEEE international conference on image processing (ICIP). IEEE, pp 4206–4210
Li B, Wang M, Li X, Tan S, Huang J (2015) A strategy of clustering modification directions in spatial image steganography. IEEE Trans Inf Forensic Secur 10(9):1905–1917
Pevny T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. In: Information hiding. Springer, pp 161–177
Qian Y, Dong J, Wang W, Tan T (2015) Deep learning for steganalysis via convolutional neural networks. SPIE Media Watermarking, Security, and Forensics, vol 9409. https://doi.org/10.1117/12.2083479
Sedighi V, Cogranne R, Fridrich J (2016) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inf Forensic Secur 11(2):221–234
Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2013) Intriguing properties of neural networks. arXiv:1312.6199
Tan S, Li B (2014) Stacked convolutional auto-encoders for steganalysis of digital images. Paper presented at the Asia-Pacific Signal and Information Processing Association 2014, Annual Summit and Conference (APSIPA)
Tang W, Tan S, Li B, Huang J (2017) Automatic steganographic distortion learning using a generative adversarial network. IEEE Signal Process Lett 24 (10):1547–1551
Tang W, Li B, Tan S, Barni M, Huang J (2019) Cnn-based adversarial embedding for image steganography. IEEE Trans Inf Forensic Secur, 1–1. https://doi.org/10.1109/TIFS.2019.2891237
Volkhonskiy D, Nazarov I, Borisenko B, Burnaev E (2017) Steganographic generative adversarial networks. arXiv:1703.05502
Xu G (2017) Deep convolutional neural network to detect j-uniward. In: Proceedings of the 5th ACM workshop on information hiding and multimedia security. ACM, pp 67–73
Xu G, Wu H, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23(5):708–712
Ye J, Ni J, Yi Y (2017) Deep learning hierarchical representations for image steganalysis. IEEE Trans Inf Forensic Secur 12(11):2545–2557
Yedroudj M, Comby F, Chaumont M (2018) Yedroudj-net: an efficient cnn for spatial steganalysis. In: ICASSP, pp 2092–2096
Zhang W, Zhang Z, Zhang L, Li H, Yu N (2017) Decomposing joint distortion for adaptive steganography. IEEE Trans Circ Syst Video Technol 27 (10):2274–2280
Zhang Y, Zhang W, Chen K, Liu J, Liu Y, Yu N (2018) Adversarial examples against deep neural network based steganalysis. In: Proceedings of the 6th ACM workshop on information hiding and multimedia security. ACM, pp 67–72
Acknowledgments
The authors would like to thank the members of DDE Laboratory in SUNY Binghamton for sharing their codes and image library, and the members of MICS Laboratory in Shenzhen University for sharing their codes. The authors would also like to thank the authors of Tensorflow and Keras.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported by NSFC under U1736214, U1636102, 61802393 and 61872356, National Key Technology R&D Program under 2016QY15Z2500, and Project of Beijing Municipal Science & Technology Commission under Z181100002718001.
Rights and permissions
About this article
Cite this article
Ma, S., Zhao, X. & Liu, Y. Adaptive spatial steganography based on adversarial examples. Multimed Tools Appl 78, 32503–32522 (2019). https://doi.org/10.1007/s11042-019-07994-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-07994-3