• D. O. Progonov Igor Sikorsky Kyiv Polytechnic Institute, Kyiv, Ukraine, Ukraine




digital image steganalysis, adaptive embedding method, image calibration, dimensionality reduction


Context. The topical problem of sensitive information protection during data transmission in local and global communication systems was considered. The case of detection of stego images formed according to novel steganographic (embedding) methods was analyzed. The object of research is special methods of stego images features pre-processing (calibration) that are used for improving detection accuracy of modern statistical stegdetectors.

Objective. The purpose of the work is performance analysis of applying special types of image calibration methods, namely divergent reference techniques, for revealing stego images formed according to adaptive embedding methods.

Method. The considered divergent reference methods are aimed at search an appropriate transformation for cover and stego images features that allows increasing Euclidean distance between them. This can be achieved by re-projection of estimated features into a high-dimensional space where cover and stego features may have higher inter-cluster distances. The work is devoted to analysis of such methods, namely by applying the inverse Fast Johnson-Lindenstrauss transform for estimation preimages of cover and stego images features. The transform allows considerably decreasing computation complexity of features calibration procedure while providing a fixed level of relative positions changes for cover and stego images features vectors, which is of particular interest in steganalysis.

Results. The dependencies of detection accuracy, namely Matthews correlation coefficient, on cover image payload and dimensionality of estimated preimages for feature vector were obtained. The case of usage state-of-the-art HUGO, S-UNIWARD, MG and MiPOD embedding methods for message hiding into a cover image was considered. Also, the variants of stego image features preprocessing by full access to stego encoder for a steganalytic as well as limited a prior information about used embedding method were analyzed.

Conclusions. The obtained experimental results proved effectiveness of proposed approach in the most difficult case of limited a prior information about used embedding method and low cover image payload (less than 10%). The prospects for further research may include investigation of applying special methods for features preimages estimation in a high-dimensional space for improving detection accuracy for advanced embedding methods.

Author Biography

D. O. Progonov, Igor Sikorsky Kyiv Polytechnic Institute, Kyiv, Ukraine

PhD, Associate Professor, Associate Professor of the Department of Information Security


Yaacoub J.-P. A., Salman O., Noura H. N., Kaaniche N., Chehab A., Malli M. Cyber-physical systems security: Limitations, issues and future trends, Microprocessors and Microsystems, 2020, Vol. 77. DOI: 10.1016/j.micpro.2020.103201.

Kaspersky Inc. Steganograph in attacks on industrial enterprises. Tech. report. Kaspersky Inc., Moscow, 2020. URL: https://ics-cert.kaspersky.com/publications/stegano-graphyin-attacks-on-industrial-enterprises/

Kodovsky J., Fridrich J. Calibration revisited, Multimedia and security: 11th ACM workshop, Princeton, 7–8 September, 2009, proceedings. Princeton, ACM, 2009, pp. 63–74. – DOI: 10.1145/1597817.1597830.

Fridrich J. Steganography in Digital Media: Principles, Algorithms, and Applications. Cambridge, Cambridge University Press, 2009, 437 p. ISBN 978–0–521–19019–0. – DOI: 10.1017/CBO9781139192903.

Konachovych G., Progonov D., Puzyrenko O. Digital steganography processing and analysis of multimedia files. Kyiv, ‘Tsentr uchbovoi literatury’ publishing, 2018, 558 p. ISBN 978-617-673-741-4.

Fridrich J., Kodovsky J. Rich models for steganalysis of digital images, IEEE Transactions on Information Forensics Security, 2012, Vol. 7, pp. 868–882. DOI: 10.1109/TIFS.2012.2190402.

Boroumand M., Chen M., Fridrich J. Deep residual network for steganalysis of digital images, IEEE Transactions on Information Forensics Security, 2018, Vol. 14, pp. 1181–1193. – DOI: 10.1109/TIFS.2018.2871749.

Tabares-Soto R., Arteaga-Arteaga H. B., Bravo-Ortiz M. A., Mora-Rubio A., Arias-Garzón D., Alzate-Grisales J. A., Burbano-Jacome A. B., Orozco-Arias S., Isaza G., RamosPollán R. GBRAS-Net: A Convolutional Neural Network Architecture for Spatial Image Steganalysis, IEEE Access, 2021, Vol. 9, pp. 14340–14350. DOI: 10.1109/ACCESS.2021.3052494.

Cohen A., Cohen A., Nissim N. ASSAF: Advanced and Slim StegAnalysis Detection Framework for JPEG images based on deep convolutional denoising autoencoder and Siamese networks, Neural Networks, 2020, Vol. 131, pp. 64–77. DOI: 10.1016/j.neunet.2020.-07.022.

Progonov D. O. Influence of digital images preliminary noising on statistical stegdetectors performance, Radio Electronics, Computer Science, Control, Vol. 1(56), 2021, pp. 184–193.

Progonov D. O. Effectiveness of stego images pre-noising with fractional noise for digital image steganalysis, Applied Aspects of Information Technology, 2021, Vol. 4, Issue 3, pp. 261–270. DOI: https://doi.org/10.15276/aait.03.2021.5

Progonov D. Statistical stegdetectors performance by message re-embedding, Theoretical and Applied Cybersecurity, 2021, Vol. 3, No. 1, pp. 5–14.

Progonov D.O. Detection Of Stego Images With Adaptively Embedded Data By Component Analysis Methods, Advances in Cyber-Physical Systems (ACPS), 2021, Vol. 6, No. 2, pp. 146–154.

Achlioptas D. Database-friendly random projections: Johnson–Lindenstrauss with binary coins, Journal of Computer and System Sciences, 2003, Vol. 66, Issue 4, pp. 671–687. DOI: 10.1016/S0022-0000(03)00025-4.

Moore E. H. On the reciprocal of the general algebraic matrix, Bulletin of the American Mathematical Society, 1920, Vol. 26, Issue 9, pp. 394–95. DOI:10.1090/S0002-9904-1920-03322-7.

Dasgupta S., Gupta A. An elementary proof of a theorem of Johnson and Lindenstrauss, Random Structures & Algorithms, 2003, Vol. 22, pp. 60–65. DOI: 10.1002/rsa.10073.

Ailon N. B., Chazelle Approximate nearest neighbors and the fast johnson-lindenstrauss transform, Proceedings of the 38th Annual Symposium on the Theory of Computing (STOC '06), 2006, Seattle, USA, pp. 557–563. DOI: 10.1145/1132516.1132597.

Lv X., Wang Z. An Extended Image Hashing Concept: Content-Based Fingerprinting Using FJLT, EURASIP Journal on Information Security, 2009, Vol. 2009, 16 p. DOI: 10.1155/2009/859859.

Pevny T., Bas P., Fridrich J. Steganalysis by subtractive pixel adjacency matrix, IEEE Transactions on Information Forensics Security, 2010, Vol. 5, pp. 215–224. DOI: 10.1109/TIFS.2010.2045842.

Cogranne R., Gilboulot Q., Bas P. The alaska steganalysis challenge: A first step towards steganalysis, Information Hiding and Multimedia Security, ACM workshop, Paris, 1–3 July, 2019: proceedings. Paris, ACM Press, 2019, pp. 125–137. – DOI: 10.1145/3335203.3335726.

Filler T., Fridrich J. Gibbs construction in steganography, IEEE Transactions on Information Forensics Security, 2010. Vol. 5, pp. 705–720. DOI: 10.1109/TIFS.2010.2077629.

Holub V., Fridrich J. Designing Steganographic Distortion Using Directional Filters, Information Forensic and Security, IEEE International Workshop, Tenerife, 2–5 December, 2012, proceedings. Tenerife, IEEE, 2012. DOI: 10.1109/WIFS.2012.6412655.

Sedighi V., Fridrich J., Cogranne R. Content-adaptive pentary steganography using the multivariate generalized gaussian cover model, Electronic Imaging, Media Watermarking, Security, and Forensics, The International Society for Optical Engineering, San Francisco, 24–26 January, 2015, proceedings. San Francisco, SPIE, 2015. DOI: 10.1117/12.2080272.

Sedighi V., Cogranne R., Fridrich J. Content adaptive steganography by minimizing statistical detectability, IEEE Transactions on Information Forensics Security, 2015, Volume 11, pp. 221–234. DOI: 10.1109/TIFS.2015.2486744.

Filler T., Fridrich J. Design of adaptive steganographic schemes for digital images, Electronic Imaging, Media Watermarking, Security, and Forensics: The Interna-tional Society for Optical Engineering, San Francisco, 24–26 January, 2011, proceedings. San Francisco, SPIE, 2011. DOI: 10.1117/12.872192.

Kodovsky J., Fridrich J. Ensemble classifiers for steganalysis of digital media, IEEE Transactions on Information Forensics Security, 2012, Vol. 7, pp. 432–444. DOI: 10.1109/TIFS.2011.2175919.

Progonov D. Performance of Statistical Stegdetectors in Case of Small Number of Stego Images in Training Set, IEEE Int. Conf. “Problems of Infocommunications Science and Technology, 2020. Kharkiv, Ukraine. DOI: https://doi.org/10.1109/PICST51311.20-20.9467901.

Chicco D., Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation, BMC Genomics volume, 2020, Vol. 21, 13 p. DOI: 0.1186/s12864-019-6413-7.

Adi B.-I., Greville T. Generalized inverses: Theory and applications, 2nd edition, 2003. New York, NY, Springer. DOI: 10.1007/b97366. – ISBN 978-0-387-00293-4.

Honeine P., Richard C. Preimage problem in kernel-based machine learning, IEEE Signal Processing Magazin, 2011, Vol. 28, Issue 2, pp. 77–88. DOI: 10.1109/MSP.2010.939747.

Cox T. F., Cox M. A. A. Multidimensional Scaling, 2nd edition, ser. Monographs on Statistics and Applied Probability, 2020. London, Chapman and Hall / CRC. DOI: 10.1007/978-3-540-33037-0_14.

Yamanishi Y., Vert J.-P. Kernel matrix regression, Tech. Rep., Cornell University library, URL: http://arxiv.org/abs/q-bio/0702054v1, 2007.




How to Cite

Progonov, D. O. (2022). EFFECTIVENESS OF STEGO IMAGE CALIBRATION VIA FEATURE VECTORS RE-PROJECTION INTO HIGH-DIMENSIONAL SPACES. Radio Electronics, Computer Science, Control, (2), 165. https://doi.org/10.15588/1607-3274-2022-2-16



Progressive information technologies