Advertisement

Determining the Parameters of the Mathematical Model of the Process of Searching for Harmful Information

  • Igor KotenkoEmail author
  • Igor Parashchuk
Chapter
Part of the Studies in Systems, Decision and Control book series (SSDC, volume 260)

Abstract

The research object is the process of detecting harmful information in social networks and the global network. The chapter proposes an approach for determining (verifying) the parameters of a mathematical model of a stochastic process for detecting harmful information with unreliable, inaccurate (contradictory) specified initial data. The approach is based on the use of stochastic equations of state and observation based on controlled Markov chains with finite differences. Moreover, the determination (verification) of key parameters of the mathematical model of this type (the elements of the matrix of one-step transition probabilities) is carried out by using an extrapolating neural network. This allows one to take into account and compensate for the inaccuracy of the original data inherent stochastic processes of searching and detecting harmful information. In addition, this approach allows one to increase the reliability of decision-making in evaluating and categorizing the digital network content for detecting and counteracting information of this class.

Keywords

Harmful information protection Mathematical model Activation function Neural network Matrix Transition probability State Estimation 

Notes

Acknowledgements

The work is performed by the grant of RSF #18-11-00302 in SPIIRAS.

References

  1. 1.
    Elahi, G., Yu, E., Zannone, N.: A modeling ontology for integrating vulnerabilities into security requirements conceptual foundations. In: Proceedings of ER-2009, pp. 99–114. Springer (2009)Google Scholar
  2. 2.
    Kotenko, I., Saenko, I., Chechulin, A., Desnitsky, V., Vitkova, L., Pronoza, A.: Monitoring and counteraction to malicious influences in the information space of social networks. In: Proceedings of 10th Social Informatics Conference (SocInfo2018), September 25–28, 2018, Saint Petersburg, Russia. Part II. Lecture Notes in Computer Science, vol. 11186, pp. 159–167. Springer (2018)Google Scholar
  3. 3.
    Kotenko, I., Saenko, I., Chechulin, A.: Protection against information in eSociety: using Data Mining methods to counteract unwanted and malicious data. In: Proc. of Digital Transformation and Global Society. In: Second International Conference DTGS. Communications in Computer and Information Science (CCIS), vol. 745, pp. 170–184 (2017)Google Scholar
  4. 4.
    Kosko, B.: Neural Networks and Fuzzy Systems. A Dynamical Systems Approach to Machine Intelligence. Prentice-Hall, Englewood Cliffs (1992)zbMATHGoogle Scholar
  5. 5.
    Kriesel, D.: A Brief Introduction to Neural Networks. Cambridge Press, Cambridge (2010)Google Scholar
  6. 6.
    Parlos, A., Menon, S., Atiya, A.: An algorithmic approach to adaptive state filtering using recurrent neural networks. IEEE Trans. Neural Netw. 12(6), 1411–1432 (2001)CrossRefGoogle Scholar
  7. 7.
    Rojas, R.: Neural Networks. Springer, Berlin (1996)CrossRefGoogle Scholar
  8. 8.
    Muller, B., Reinhardt, J., Strickland, M.: Neural Networks: An Introduction. Springer (1995)Google Scholar
  9. 9.
    Anderson, J., Rosenfeld, E.: Neurocomputing: Foundation of Research. MIT Press, Cambridge (1988)Google Scholar
  10. 10.
    Nesteruk, G., Kupriyanov, M.: Neural-fuzzy systems with fuzzy links. In: Proceedings of the VI-th International Conference SCM’2003. St.Pb, StPSETU «LETI», vol. 1, pp. 341–344 (2003)Google Scholar
  11. 11.
    Kotenko, I., Parashchuk, I., Omar, T.: Neuro-fuzzy models in tasks of intelligent data processing for detection and counteraction of inappropriate, dubious and harmful information. In: Proceedings of the 2nd International Scientific-Practical Conference Fuzzy Technologies in the Industry (FTI-2018). CEUR Workshop Proceedings (CEUR-WS), vol. 2258, pp. 116–125 (2018)Google Scholar
  12. 12.
    Parashchuk, I.: System formation algorithm of communication network quality factors using artificial neural networks. In: Proceedings of 1st IEEE International Conference on Circuits and System for Communications (ICCSC’02), St.Pb, SPbGTU, pp. 263–266 (2002)Google Scholar
  13. 13.
    Stewart, N., Thomas, G.: Markov processes. In: Proceedings of Probability and Mathematical Statistics, pp. 214–234. Wiley, New York (1986)Google Scholar
  14. 14.
    Bini, D., Latouche, G., Meini, B.: Numerical Methods for Structured Markov Chains. Oxford University Press, New York (2005)CrossRefGoogle Scholar
  15. 15.
    Yuksel, S.: Control of Stochastic Systems. Queen’s University Mathematics and Engineering and Mathematics and Statistics (2017)Google Scholar
  16. 16.
    Van Handel, R.: Stochastic Calculus, Filtering and Stochastic Control. Springer (2007)Google Scholar
  17. 17.
    Dobre, T.: In: T.G. Dobre, J.G. Sanchez Marcano (eds.) Chemical Engineering: Modeling, Simulation and Similitude. Wiley, Weinheim (2007)Google Scholar
  18. 18.
    Oliver, D., Kelliher, T., Keegan, J.: Engineering Complex Systems With Models and Objects. McGraw-Hill, New York (2007)Google Scholar
  19. 19.
    Oksendal, B.: Stochastic Differential Equations. An Introduction with Applications. Springer, Berlin (2007)zbMATHGoogle Scholar
  20. 20.
    Iacus, S.: Simulation and Inference for Stochastic Differential Equations. With R Examples. Springer, New York (2008)CrossRefGoogle Scholar
  21. 21.
    Quarteroni, A.: Mathematical Models in Science and Engineering. Proc. Not. AMS 56(1), 9–19 (2009)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.St. Petersburg Institute for Informatics and Automation of Russian Academy of Sciences (SPIIRAS)St. PetersburgRussia

Personalised recommendations