The software complex for attack the linguistic stegosystem

Authors

  • Ярослав Володимирович Тарасенко Черкаський державний технологічний університет, Україна

DOI:

https://doi.org/10.18372/2225-5036.24.12388

Keywords:

attacks on stegosystems, software complex, linguistic steganography, counteracting the methods of steganography, semantic compression, steganalysis, textual steganography, automated steganalysis, linguistic systems of steganalysis

Abstract

The article reviews the common methods and algorithms of textual steganalysis and text summarization, as well as automated computer systems based on them. It is described the disadvantages for accomplishing the task of the linguistic stegosystem attacking by semantic compression in order to remove a hidden message. The article describes the development and pre-testing of the software complex, based on the semantic compression of the text for attacking the linguistic stegosystem and taking into account the initial structure of this text. The development is aimed at detecting and neutralizing the threats caused by the use of computer linguistic steganography methods. Described program complex consists of 9 interconnected modules, 25 systems and 6 subsystems. Their interaction is highlighted and the system’s algorithm is shown in the article. The pre-testing results on the basis of the material consisting of 1000 generated texts, divided into such two categories, as the stegomessage hiding method and the volume of text, prove the effectiveness of the attack using the proposed program. The stegomessage may be deleted by 97%, the average compression ratio is 2.5 for single sentences and 4.6 for solid texts. During the preliminary testing it was found the main advantages of the system, which include the automation the process of attacking a text-based stegosystem using both meaningful and meaningless texts and a wide range of research in stegoanalysis. Thus, the efficiency and practical capacity of the developed author's method, aimed at the textual data semantic compression for the purpose of counteracting the methods of linguistic steganography, has been proved. The further studies will be related to elimination the disadvantages detected during the preliminary testing and to confirming the preliminary conclusions of the work.

Author Biography

Ярослав Володимирович Тарасенко, Черкаський державний технологічний університет, Україна

Рік та місце народження: 1993 рік, м. Черкаси, Україна.

Освіта: Черкаський державний технологічний університет, 2015 рік;

Черкаський державний технологічний університет, 2016 рік.

Посада: аспірант кафедри інформаційної безпеки та комп’ютерної інженерії.

Наукові інтереси: комп’ютерна лінгвістична стеганографія, математична та

прикладна лінгвістика, інформаційна безпека, комп’ютерні системи.

Публікації: 7 наукових публікацій.

References

K. Vineet, «The Changing World of Media & Communication», Journal of Mass Communication & Journalism,URL: https://www.omicsonline.org/open-access/the changing-world-of-media-and-communication21657912 .1000116.php ?aid=6473.

І. Федотова-Півень, Я. Тарасенко, «Шляхи задоволення потреб сучасної кібербезпеки в рамках протидії методам комп’ютерної лінгвістичної стеганографії», Безпека інформації, №23(3), с. 190-196, 2017.

R. Neha, J. Chaudhary, «Text Steganography Techniques: A Review», International Journal of Engineering Trends and Technology, Vol. 4, Issue 7, pp. 3013-3015, 2013.

О. Бабина, «Лингвистическая стеганография: современные подходы. Часть 2», Вестник ЮУрГУ. Серия: Лингвистика, №4, с. 49-55, 2015.

P. Meng, L. Hang, Z. Chen, Y. Hu, W. Yang, «STBS: A Statistical Algorithm for Steganalysis of Translation-Based Steganography», 12th International Conference «Information Hiding», Calgary, Canada, June 28-30, Vol. 6387, pp. 208-220, 2010.

Z. Chen, L. Huang, Z. Yu, W. Yang, L. Li, X. Zheng, X. Zhao, «Linguistic Steganography Detection Using Statistical Characteristics of Correlations between Words», 10th International Workshop «Information Hiding», Santa Barbara, USA, May 19-21, Vol. 5284, pp. 224-235, 2008.

Z. Chen, L. Huang, Z. Yu, L. Li, W. Yang, «A Statistical Algorithm for Linguistic Steganography Detection Based on Distribution of Words», Third International Conference on Availability, Reliability and Security, Barcelona, Spain, March 04-07, pp. 558 – 563, 2008.

Z. Chen, L. Huang, Z. Yu, X. Zhao, X. Zhao, «Effective Linguistic Steganography Detection», 8th International Conference on Computer and Information Technology Workshops, Sidney, Australia, July 08-11, pp. 224-229, 2008.

Y. Gong, X. Liu, «Generic text summarization using relevance measure and latent semantic analysis», Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Informational Retrieval, New Orleans, USA, September 9-12, pp. 19-25, 2001.

J. Conroy, D. O’leary, «Text summarization via hidden markov models», Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Informational Retrieval, New Orleans, USA, September 9-12, pp. 406-407, 2001.

D. Radev, H. Jing, M. Stys, D. Tam, «Centroid-based summarization of multiple documents», Information Processing & Management, №40(6), pp. 919-938, 2004.

R. Paulus, C. Xiong, R. Socher «A Deep Reinforced Model for Abstractive Summarization», May 2017, URL: https://arxiv.org/ab s/1705.04304.

Issue

Section

Steganography & Steganalysis