Image Steganalysis using Deep Convolution Neural Networks: A Literature Survey


Citar

Texto integral

Resumo

:Steganography is the technique of hiding data for secret communication in a public media format. The image in which the hidden data is stored is called a stego image. Steganalysis is the process of targeting the methods of steganography to identify, remove, destroy, and exploit the secret data in stego images. The identification of embedded secret data in the image is the basis for steganalysis. The proper selection of the type and composition of cover files contributes to a better embedding. Several steganalysis techniques exist for detecting steganography in the images given. Because of the embedded data, the performance of the steganalysis technique relies on the capacity to retrieve the feature representations to identify the statistical portion of the image. Steganalysis & steganography has experienced tremendous development in recent years with the emergence of Deep Convolution Neural Networks (DCNN). In this paper, we explored the current state of research from the latest systems of image steganalysis based on deep learning. This paper presents different methodologies and frameworks of CNN, the research being carried out on image steganalysis based on deep learning and implementation complexities, and highlights the benefits and limitations of the existing techniques. This study also provides the direction for future research and may serve as a fundamental source for further research in deep learning-based image steganalysis.

Sobre autores

Numrena Farooq

Department of Computer Science and Engineering, National Institute of Technology Srinagar

Autor responsável pela correspondência
Email: info@benthamscience.net

Roohie Mir

Department of Computer Science and Engineering, National Institute of Technology Srinagar

Email: info@benthamscience.net

Bibliografia

  1. Hussain I, Zeng J. A survey on deep convolutional neural networks for image steganography and steganalysis. Trans Internet Inf Syst (Seoul) 2020; 14(3): 1228-48. doi: 10.3837/tiis.2020.03.017
  2. JinaChanu Y, Manglem Singh K, Tuithung T. Image steganography and steganalysis: A survey. Int J Comput Appl 2012; 52(2): 1-11. doi: 10.5120/8171-1484
  3. Pevný T, Filler T, Bas P. Using high-dimensional image models to perform highly undetectable steganography Information Hiding. Berlin, Heidelberg: Springer Link 2010. doi: 10.1007/978-3-642-16435-4_13
  4. Li B, Wang M, Huang J, Li X. A new cost function for spatial image steganography. 2014 IEEE Int Conf Image Process ICIP 2014. 29 January 2015; Paris, France. 2014; pp. 4206-10. doi: 10.1109/ICIP.2014.7025854
  5. Holub V, Fridrich J. Designing steganographic distortion using directional filters. 2012 IEEE International Workshop on Information Forensics and Security (WIFS). 02-05 December 2012; Costa Adeje, Spain. 2012. doi: 10.1109/WIFS.2012.6412655
  6. Holub V, Fridrich J, Denemark T. Universal distortion function for steganography in an arbitrary domain. EURASIP J Multimed Inf Secur 2014; 2014(1): 1-13. doi: 10.1186/1687-417X-2014-1
  7. Jin Z, Yang Y, Chen Y, Chen Y. IAS-CNN: Image adaptive steganalysis via convolutional neural network combined with selection channel. Int J Distrib Sens Netw 2020; 16(3): 2. doi: 10.1177/1550147720911002
  8. Westfeld A. F5-A steganographic algorithm high capacity despite better steganalysis. Information Hiding 2001.
  9. Pan Y, Ni J, Su W. Improved uniform embedding for efficient JPEG steganography Cloud Computing And Security. Berlin, Heidelberg: Springer Link 2016. doi: 10.1007/978-3-319-48671-0_12
  10. Guo L, Ni J, Su W, Tang C, Shi YQ. Using statistical image model for JPEG Steganography: Uniform embedding Revisited. IEEE Trans Inf Forensics Security 2015; 10(12): 2669-80. doi: 10.1109/TIFS.2015.2473815
  11. Reinel T-S, Raúl RP, Gustavo I. Deep learning applied to steganalysis of digital images: A systematic review. IEEE Access 2019; 7: 68970-90. doi: 10.1109/ACCESS.2019.2918086
  12. Liu F, Yan X, Lu Y. Feature selection for image steganalysis using binary bat algorithm. IEEE Access 2020; 8: 4244-9. doi: 10.1109/ACCESS.2019.2963084
  13. L R, B L. Approaches and methods for Steganalysis – A survey. Int J Adv Res Comput Commun Eng 2017; 6(6): 433-8. doi: 10.17148/IJARCCE.2017.6678
  14. Kim DH, Lee HY. Deep learning-based steganalysis against spatial domain steganography. 2017 European Conference on Electrical Engineering and Computer Science (EECS). 17-19 November 2017; Bern, Switzerland. 2018; pp. 1-4. doi: 10.1109/EECS.2017.9
  15. Fridrich J, Kodovsky J. Rich models for steganalysis of digital images. IEEE Trans Inf Forensics Security 2012; 7(3): 868-82. doi: 10.1109/TIFS.2012.2190402
  16. Kodovský J, Fridrich J, Holub V. Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Forensics Security 2012; 7(2): 432-44. doi: 10.1109/TIFS.2011.2175919
  17. Chang CC, Lin CJ. LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2011; 2(3): 1-27. doi: 10.1145/1961189.1961199
  18. Ozcan S, Mustacoglu AF. Transfer learning effects on image steganalysis with pre-trained deep residual neural network model. Big Data 2018; 2018: 2280-7. doi: 10.1109/BigData.2018.8622437
  19. Qian Y, Dong J, Wang W, Tan T. Deep learning for steganalysis via convolutional neural networks. Proceedings of SPIE - The International Society for Optical Engineering 9409. San Francisco, California, United States 2015; p. 10. doi: 10.1117/12.2083479
  20. Poultney C, Chopra S, Cun YL. Efficient learning of sparse representations with an energy-based model. Adv Neural Inf Process Syst 2006; 1137-44.
  21. Bengio Y, Lamblin P, Popovici D, Larochelle H. Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 2007; (1): 153-60.
  22. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521(7553): 436-44. doi: 10.1038/nature14539 PMID: 26017442
  23. Yang P, Baracchi D, Ni R, Zhao Y, Argenti F, Piva A. A survey of deep learning-based source image forensics. J Imaging 2020; 6(3): 9. doi: 10.3390/jimaging6030009 PMID: 34460606
  24. Szegedy C. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 07-12 June 2015; Boston, MA, USA 2015; pp. 1-9. doi: 10.1109/CVPR.2015.7298594
  25. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:14091556 2015.
  26. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 27-30 June 2016; Las Vegas, NV, USA. 2016; pp. 770-8. doi: 10.1109/CVPR.2016.90
  27. Wu S, Zhong S, Liu Y. Deep residual learning for image steganalysis Multimedia Tools and Applications. Berlin, Heidelberg: Springer Link 2017. doi: 10.1007/s11042-017-4440-4
  28. Khan A, Sohail A, Zahoora U, Qureshi AS. A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 2020; 53(8): 5455-516. doi: 10.1007/s10462-020-09825-6
  29. Phung VH, Rhee EJ. A High-accuracy model average ensemble of convolutional neural networks for classification of cloud image patches on small datasets. Appl Sci (Basel) 2019; 9(21): 4500. doi: 10.3390/app9214500
  30. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM 2017; 60(6): 84-90. doi: 10.1145/3065386
  31. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 21-26 July 2017; Honolulu, HI, USA. 2017. doi: 10.1109/CVPR.2017.243
  32. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 12 December 2016; Las Vegas, NV, USA. 2016; pp. 2818-26. doi: 10.1109/CVPR.2016.308
  33. Szegedy C, Ioffe S, Vanhoucke V, Alemi AA. Inception-v4, inception- ResNet and the impact of residual connections on learning 31st AAAI Conf Artif Intell AAAI 2017; 2017; 31(1): 4278-84. doi: 10.1609/aaai.v31i1.11231
  34. Zeiler MD, Fergus R. Visualizing and understanding convolutional networks Computer Vision – ECCV 2014. Berlin, Heidelberg: SpringerLink 2014. doi: 10.1007/978-3-319-10590-1_53
  35. Tian J, Li Y. Convolutional neural networks for steganalysis via transfer learning. Int J Pattern Recognit Artif Intell 2019; 33(2): 1959006. doi: 10.1142/S0218001419590067
  36. Kaur R, Kaur B. Licensed under creative commons attribution CC BY A study and review of techniques of spatial steganography. Int J Sci Res 2013; 4(4): 3198-203.
  37. Tan S, Li B. Stacked convolutional auto-encoders for steganalysis of digital images. Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific. 16 February 2015; Siem Reap, Cambodia 2014. doi: 10.1109/APSIPA.2014.7041565
  38. Pevny T. Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inf Forensics Security 2009; 5(215): 224.
  39. Qian Y, Dong J, Wang W, Tan T. Learning and transferring representations for image steganalysis using convolutional neural network. 2016 IEEE International Conference on Image Processing (ICIP). 19 August 2016; Phoenix, AZ, USA. 2016. doi: 10.1109/ICIP.2016.7532860
  40. Xu G, Wu HZ, Shi YQ. Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 2016; 23(5): 708-12. doi: 10.1109/LSP.2016.2548421
  41. Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv:150203167 2015.
  42. Xu G, Wu HZ, Shi YQ. Ensemble of CNNs for steganalysis : An empirical study Information Hiding and Multimedia Security. New York, NY, United States: Association for Computing Machinery 2016; pp. 103-7. doi: 10.1145/2909827.2930798
  43. Pibre L, Pasquet J, Ienco D, Chaumont M. Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch. arXiv:151104855 2016. doi: 10.2352/ISSN.2470-1173.2016.8.MWSF-078
  44. Couchot J-F, Couturier R, Guyeux C, Salomon M. Steganalysis via a convolutional neural network using large convolution filters for embedding process with same stego key. arXiv:160507946 2016.
  45. Sedighi V, Fridrich J. Histogram layer, moving convolutional neural networks towards feature-based steganalysis. Electron Imaging 2017; 2017(7): 50-5. doi: 10.2352/ISSN.2470-1173.2017.7.MWSF-325
  46. Holub V, Fridrich J. Random projections of residuals for digital image steganalysis. IEEE Trans Inf Forensics Security 2013; 8(12): 1996-2006. doi: 10.1109/TIFS.2013.2286682
  47. Ye J, Ni J, Yi Y. Deep Learning Hierarchical Representations for Image Steganalysis. IEEE Trans Inf Forensics Security 2017; 12(11): 2545-57. doi: 10.1109/TIFS.2017.2710946
  48. Wu S, Zhong S, Liu Y. A novel convolutional neural network for image steganalysis with shared normalization. IEEE Trans Multimed 2020; 22(1): 256-70. doi: 10.1109/TMM.2019.2920605
  49. Li B, Wei W, Ferreira A, Tan S. ReST-Net: Diverse activation modules and parallel subnets-based CNN for spatial image steganalysis. IEEE Signal Process Lett 2018; 25(5): 650-4. doi: 10.1109/LSP.2018.2816569
  50. Yedroudj M, Comby F, Chaumont M. Yedroudj-Net: An efficient CNN for spatial steganalysis. arXiv:180300407 2018. doi: 10.1109/ICASSP.2018.8461438
  51. Zhang R, Zhu F, Liu J, Liu G. Efficient feature learning and multisize image steganalysis based on CNN. arXiv:180711428 2018.
  52. Dengpan Y, Shunzhi J, Shiyu L. Faster and transferable deep learning steganalysis on GPU. J Real-Time Image Process 2019; 16: 623-33. doi: 10.1007/s11554-019-00870-1
  53. Kato H, Osuge K, Haruta S, Sasase I. A preprocessing by using multiple steganography for intentional image downsampling on CNN-based steganalysis. IEEE Access 2020; 8: 195578-93. doi: 10.1109/ACCESS.2020.3033814
  54. Ntivuguruzwa JDLC, Ahmad T. A convolutional neural network to detect possible hidden data in spatial domain images. Cyber Secur 2023; 6(1): 23. doi: 10.1186/s42400-023-00156-x
  55. Reinel TS, Brayan A-AH, Alejandro B-OM, et al. GBRAS-Net: A convolutional neural network architecture for spatial image steganalysis. IEEE Access 2021; 9(January): 14340-50. doi: 10.1109/ACCESS.2021.3052494
  56. Duan X, Zhang C, Ma Y, Liu S. Preprocessing enhancement method for spatial domain steganalysis. Mathematics 2022; 10(21): 3936. doi: 10.3390/math10213936
  57. Liu S, Zhang C, Wang L, Yang P, Hua S, Zhang T. Image steganalysis of low embedding rate based on the attention mechanism and transfer learning. Electronics (Basel) 2023; 12(4): 969. doi: 10.3390/electronics12040969
  58. Bravo-Ortiz MA, Mercado-Ruiz E, Villa-Pulgarin JP, et al. CVTStego-Net: A convolutional vision transformer architecture for spatial image steganalysis. J Inf Secur Appl 2024; 81(January): 103695. doi: 10.1016/j.jisa.2023.103695
  59. Xu G. Deep convolutional neural network to detect J-UNIWARD Information Hiding and Multimedia Security. New York, NY, United States: Association for Computing Machinery 2017; pp. 67-73. doi: 10.1145/3082031.3083236
  60. Zeng J, Tan S, Li B, Huang J. Large-scale JPEG Image Steganalysis using hybrid deep-learning framework. IEEE Trans Inf Forensics Security 2018; 13(5): 1200-14. doi: 10.1109/TIFS.2017.2779446
  61. Zhong K, Feng G, Shen L, Luo J. Deep learning for steganalysis based on filter diversity selection. Sci China Inf Sci 2018; 61(12): 129105. doi: 10.1007/s11432-018-9640-7
  62. Chen M, Sedighi V, Boroumand M, Fridrich J. JPEG-phase-aware convolutional neural network for steganalysis of JPEG images Information Hiding and Multimedia Security. New York, NY, United States: Association for Computing Machinery 2017; pp. 75-84. doi: 10.1145/3082031.3083248
  63. Yang J, Shi Y-Q, Wong EK, Kang X. JPEG Steganalysis based on DenseNet. arXiv:171109335 2017.
  64. Hu D, Zhou S, Shen Q, Zheng S, Zhao Z, Fan Y. Digital Image Steganalysis based on visual attention and deep reinforcement learning. IEEE Access 2019; 7(c): 25924-35. doi: 10.1109/ACCESS.2019.2900076
  65. Deng XQ, Chen BL, Luo WQ, Luo D. Universal Image steganalysis based on convolutional neural network with global covariance pooling. J Comput Sci Technol 2022; 37(5): 1134-45. doi: 10.1007/s11390-021-0572-0
  66. Liu Q, Yang Z, Wu H. JPEG Steganalysis based on Steganographic feature enhancement and graph attention learning. J Electron Imaging 2023; 32(3): 1-10. doi: 10.1117/1.JEI.32.3.033032
  67. Mo C, Liu F, Zhu M, Yan G, Qi B, Yang C. Image Steganalysis based on deep content features clustering. Comput Mater Continua 2023; 76(3): 2921-36. doi: 10.32604/cmc.2023.039540
  68. Zhang J, Zhao X, He X. Robust JPEG steganography based on the robustness classifier. EURASIP J Inf Secur 2023; 2023(1): 11. doi: 10.1186/s13635-023-00148-x
  69. Yang J, Kang X, Wong EK, Shi YQ. Deep learning with feature reuse for JPEG image steganalysis. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) doi: 10.23919/APSIPA.2018.8659589
  70. Qian Y, Dong J, Wang W, Tan T. Feature learning for steganalysis using convolutional neural networks. Multimedia Tools Appl 2018; 77(15): 19633-57. doi: 10.1007/s11042-017-5326-1
  71. Lu YY, Yang ZLO, Zheng L, Zhang Y. Importance of truncation activation in pre-processing for spatial and Jpeg image steganalysis. 2019 IEEE International Conference on Image Processing (ICIP). 22-25 September 2019; Taipei, Taiwan. 2019. doi: 10.1109/ICIP.2019.8803800
  72. Zeng J, Tan S, Liu G, Li B, Huang J. WISERNet: Wider separate-then-reunion network for steganalysis of color images. IEEE Trans Inf Forensics Security 2019; 14(10): 2735-48. doi: 10.1109/TIFS.2019.2904413
  73. Zhang T, Zhang H, Wang R, Wu Y. A new JPEG image steganalysis technique combining rich model features and convolutional neural networks. Math Biosci Eng 2019; 16(5): 4069-81. doi: 10.3934/mbe.2019201 PMID: 31499650
  74. Boroumand M, Chen M, Fridrich J. Deep residual network for steganalysis of digital images. IEEE Trans Inf Forensics Security 2019; 14(5): 1181-93. doi: 10.1109/TIFS.2018.2871749
  75. Tabares-Soto R, Arteaga-Arteaga HB, Mora-Rubio A, et al. Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain. PeerJ Comput Sci 2021; 7: e451. doi: 10.7717/peerj-cs.451 PMID: 33954236
  76. Shankar DD, Azhakath AS. Random embedded calibrated statistical blind steganalysis using cross validated support vector machine and support vector machine with particle swarm optimization. Sci Rep 2023; 13(1): 2359. doi: 10.1038/s41598-023-29453-8 PMID: 36759703
  77. Ozcan S, Mustacoglu AF. Transfer Learning effects on image steganalysis with pre-trained deep residual neural network model. 2018 IEEE International Conference on Big Data (Big Data). 10-13 December 2018; Seattle, WA, USA. 2018. doi: 10.1109/BigData.2018.8622437
  78. Shankara DD, Upadhyay PK. Blind steganalysis for JPEG images using SVM and SVM-PSO classifiers. Int J Innov Technol Explor Eng 2019; 8(11S): 1-8. doi: 10.35940/ijitee.K1250.09811S19
  79. Kishore A. Deep learning approaches to universal and practical steganalysis 2020.

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar

Declaração de direitos autorais © Bentham Science Publishers, 2024