Information and Communication Engineering | Article | Published 2022

Development a Model of a Network Attack Detection in Information and Communication Systems

Authors:

Sherzod Gulomov

Collection: Journal of Advances in Information Technology
Keywords: Support Vector Machine (SVM), data mining methods, fuzzy logic, clustering methods

Abstract

In this paper the possibility of distribution of Intrusion Detection System (IDS) functionality and Data Mining methods and tools for detecting attacks are analyzed as well variants of placement of the network attack detection system components and application of support vector machine for detecting attacks in a distributed computer network is proposed. The method of principal components which allows to form a feature space for detecting a given set of vectors (network attacks), as well as to reduce the amount of information stored in the base of decision rules necessary for classifying a network. packets, and increase the speed of formation of detection modules is presented. The scheme for applying dimension reduction methods, diagram of the application of clustering methods and its fuzzy inference mechanism is improved. Scheme of formation of detection modules, the variants of placement of functional blocks of the system for detecting network attacks in a separate node and the place of the detection module in the adaptive system are worked out.

References

  1. REFERENCES
  2. [1] S. K. Dey, M. M. Rahman, and M. R. Uddin, “Detection of flowbased
  3. anomaly in openflow controller: Machine learning approach
  4. in software defined networking,” in Proc. 4th International
  5. Conference on Electrical Engineering and Information
  6. Communication Technology, 2018, pp. 416-421
  7. [2] R. K. Malaiya, D. Kwon, S. C. Suh, H. Kim, I. Kim, and J. Kim,
  8. “An empirical evaluation of deep learning for network anomaly
  9. detection,” IEEE Access, vol. 7, pp. 140806-140817, 2019.
  10. [3] M. Gao, L. Ma, H. Liu, Z. Zhang, Z. Ning, and J. Xu, “Malicious
  11. network traffic detection based on deep neural networks and
  12. association analysis,” Sensors, vol. 20, p. 1452, 2020.
  13. [4] Y. Zhang, P. Li, and X. Wang, “Intrusion detection for IoT based
  14. on improved genetic algorithm and deep belief network,” IEEE
  15. Access, vol. 7, pp. 31711-31722, 2019.
  16. [5] J. Ye, X. Cheng, J. Zhu, L. Feng, and L. Song, “A DDoS attack
  17. detection method based on SVM in software defined network,”
  18. Secur. Commun. Netw., p. 9, 2018.
  19. [6] S. K. Dey and M. M. Rahman, “Effects of machine learning
  20. approach in flow-based anomaly detection on software-defined
  21. networking,” Symmetry, p. 19, 2020.
  22. [7] Y. Gan, “Application analysis of data mining in the field of
  23. computer network security,” China New Communications, p. 159,
  24. 2018.
  25. [8] B. Ghaddar and J. Naoum-Sawaya, “High dimensional data
  26. classification and feature selection using support vector machines,”
  27. Eur. J. Oper. Res., vol. 265, pp. 993-1004, 2018.
  28. [9] S. K. Biswas, “Intrusion detection using machine learning a
  29. comparison study,” International Journal of Pure and Applied
  30. Mathematics, vol. 118, no. 19, pp. 101-114, 2018.
  31. [10] N. Sultana, N. Chilamkurti, W. Peng, and R. Alhadad, “Survey on
  32. SDN based network intrusion detection system using machine
  33. learning approaches,” Peer Netw. Appl., vol. 12, pp. 493-501, 2019.
  34. [11] C. J. Ugochukwu and E. O Bennett, “An intrusion detection system
  35. using machine learning algorithm,” International Journal of
  36. Computer Science and Mathematical Theory, vol. 4, no. 1, 2018.
  37. [12] N. Ryabchuk, et al., “Artificial intelligence technologies using in
  38. social engineering attacks,” in Proc. CEUR Workshop Proceedings.
  39. Vol-2654: Proceedings of the International Workshop on Cyber
  40. Hygiene, Kyiv, Ukraine, November 30, 2019, pp. 546-555.
  41. [13] K. Molodetska, Y. Brodskiy, and S. Fedushko, “Model of
  42. assessment of information-psychological influence in social
  43. networking services based on information insurance,” in Proc.
  44. CEUR Workshop Proceedings. Vol 2616: Proceedings of the 2nd
  45. International Workshop on Control, Optimisation and Analytical
  46. Processing of Social Networks, Lviv, Ukraine, May 21, 2020, pp.
  47. 187-198.
Loading...
0

Views

0

Reads

0

Comments

0

Reviews

0

Liked

0

Shared

0

Bibliography

0

Citations

Like and share on

Cite this publication

Copy text below and use in your article