Advertisement

Method for Predicting Pixel Values in Background Areas in the Problem of Weighted Steganalysis in the Spatial Domain of Natural Images Under Small Payloads

  • Daniil A. BashmakovEmail author
  • Anatoliy G. Korobeynikov
  • Alexey V. Sivachev
  • Didier El Baz
  • Dmitry Levshun
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 971)

Abstract

The problem of effective counteraction to the malicious data transfer channels is of importance in any area where data transfer is performed. One of the aspects of the Mobile Internet Security is detecting such channels, regardless the way these channels are organized. Steganography is one of the ways to interact without attracting attention, and still digital image is one of the most popular steganographic containers nowadays. The effectiveness of the weighted steganalysis of still digital images in the spatial domain in the task of determining the fact of embedding in the least significant bits of the images with a significant fraction of a homogeneous background is discussed. A definition of the concept of a homogeneous background of a natural digital image in the steganalysis problem is given. The connection of the fraction of a homogeneous background in the image with the efficiency of a weighted steganalysis of the image is shown. The connection between the accuracy of the prediction of the pixel values in the background areas of images and the effectiveness of steganalysis in such is shown. A method for predicting the pixel values of background images has been developed, which makes it possible to improve the efficiency of weighted steganalysis of images with a significant fraction of a homogeneous background by 3–8%. The data of numerical estimates of the increase in the effectiveness of steganalysis are presented using the proposed method for predicting pixel values in background areas.

Keywords

Steganography Steganoimage Steganalysis Binary classification Weighted steganalysis Method of steganalysis WeightedStegoImage Background area of image LSB-steganography Least significant bit 

Notes

Acknowledgements

This work was supported by Government of Russian Federation (Grant 08-08).

References

  1. 1.
    Kolomeec, M., Checulin, A., Pronoza, A., Kotenko, I.: Technique of data visualization: example of network topology display for security monitoring. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. (JoWUA) 7(1), 58–78 (2016)Google Scholar
  2. 2.
  3. 3.
    Hashem, Y., Takabi, H., GhasemiGol, M., Dantu, R.: Inside the mind of the insider: towards insider threat detection using psychophysiological signals. J. Internet Serv. Inf. Secur. (JISIS) 6(1), 20–36 (2016)Google Scholar
  4. 4.
    Bordel, B., Alcarria, R., Manso, M.A., Jara, A.: Building enhanced environmental traceability solutions: from thing-to-thing communications to generalized cyber-physical systems. J. Internet Serv. Inf. Secur (JISIS) 7(3), 17–33 (2017)Google Scholar
  5. 5.
    Gayathri, C., Kalpana, V.: Study on image steganography techniques. Int. J. Eng. Technol. (IJET) 5, 572–577 (2013)Google Scholar
  6. 6.
    Kotenko, I., Saenko, I., Kushnerevich, A.: Parallel big data processing system for security monitoring in Internet of Things networks. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. (JoWUA) 8(4), 60–74 (2017)Google Scholar
  7. 7.
    Prokhozhev, N., Mikhailichenko, O., Sivachev, A., Bashmakov, D., Korobeynikov, A.: Passive steganalysis evaluation: reliabilities of modern quantitative steganalysis algorithms. In: Abraham, A., Kovalev, S., Tarassov, V., Snášel, V. (eds.) Proceedings of the First International Scientific Conference “Intelligent Information Technologies for Industry” (IITI 2016). AISC, vol. 451, pp. 89–94. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-33816-3_9CrossRefGoogle Scholar
  8. 8.
    Fridrich, J., Goljan, M.: On estimation of secret message length in LSB steganography in spatial domain. In: Proceedings of SPIE, Security, Steganography, and Watermarking of Multimedia Contents VI, vol. 5306 (2004).  https://doi.org/10.1117/12.521350
  9. 9.
    Ker, A.: A Weighted stego image detector for sequential LSB replacement. In: Proceedings - IAS 2007 3rd International Symposium on Information Assurance and Security, pp. 453–456 (2007).  https://doi.org/10.1109/ias.2007.71
  10. 10.
    Ker, A., Böhme, R.: Revisiting weighted stego-image steganalysis. In: Proceedings of SPIE, Security, Forensics, Steganography, and Watermarking of Multimedia Contents X, vol. 6819 (2008).  https://doi.org/10.1117/12.766820
  11. 11.
    Yu, X., Babaguchi, N.: Weighted stego-Image based steganalysis in multiple least significant bits. In: 2008 IEEE International Conference on Multimedia and Expo, Hannover, pp. 265–268 (2008)Google Scholar
  12. 12.
    Bashmakov, D.: Adaptive pixel pixel prediction in gradient areas to improve the accuracy of steganoanalysis in still digital images. Cybern. Program. (2), 83–93 (2018).  https://doi.org/10.25136/2306-4196.2018.2.25514
  13. 13.
    Break Our Watermarking System (BOWS) image database. http://bows2.ec-lille.fr
  14. 14.
    Break Our Steganographic System (BOSS) image database. http://agents.fel.cvut.cz/boss/index.php?mode=VIEW&tmpl=materials
  15. 15.
  16. 16.
    Places image database. http://places2.csail.mit.edu/

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Saint Petersburg National Research University of Information Technologies, Mechanics and Optics, (ITMO University)St. PetersburgRussia
  2. 2.Pushkov Institute of Terrestrial Magnetism, Ionosphere and Radio Wave Propagation of the Russian Academy of Sciences St.-Petersburg Filial (SPbF IZMIRAN)St. PetersburgRussia
  3. 3.LAAS-CNRS, Universite de Toulouse, CNRSToulouseFrance

Personalised recommendations