Advertisement

Network Intrusion Detection System Using Soft Computing Technique—Fuzzy Logic Versus Neural Network: A Comparative Study

  • Srinivas MishraEmail author
  • Sateesh Kumar Pradhan
  • Subhendu Kumar Rath
Conference paper
  • 33 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1040)

Abstract

Security of a data framework is its significant property, particularly today, when PCs are interconnected by means of web. Since no framework can be completely secure, the opportune and precise recognition of interruptions is essential. For this reason, intrusion detection systems (IDS) were planned. An interruption identification framework’s principle aspiration is to sort exercises of a framework into two key classes: standard and suspicious exercises. Most IDS business devices are abuse frameworks with principle-based master framework structure. Be that as it may, these strategies are less effective when assault qualities shift from inherent marks. In such manner, a scope of pre-preparing practices, for example, information mining, neural systems, Petri nets, state change outlines, hereditary calculations, choice trees and fluffy-based rationales is worked out. In this paper, we have considered distinctive fluffy methodologies for interruption identification framework utilizing fuzzy set hypothesis, and we dissect fuzzy standard, expressly for peculiarity-based assault finding. For structure inconsistency framework, neural systems likewise can be utilized, on the grounds that they can figure out how to segregate the ordinary and anomalous conduct of a framework from models. Along these lines, they offer a promising strategy for structure oddity frameworks. Fake neural systems give the possibility to recognize and arrange organized action dependent on constrained, fragmented and nonlinear information sources. We have completed a similar report between two delicate registering procedures utilization of fluffy in the event that principles versus use of the feed forward neural network prepared by back-propagation calculation for interruption location. Reenactment result demonstrates that the feed forward neural network prepared by back-propagation calculation for interruption location yields better outcome which distinguishes the interruptions precisely and is well reasonable for constant applications as contrasted and fluffy on the off chance that rules.

Keywords

Intrusion detection system Fuzzy logic Fuzzy if–then rule Back-propagation neural network Feed forward neural network Soft computing 

References

  1. 1.
    Mishra, S., Pradhan, S.K., Rath, S.K.: Network intrusion detection system using fuzzy if-then rules and fuzzy reasoning: a soft computing technique. Int. J. Comput. Eng. Appl. XII(IV), 301–310 (2018)Google Scholar
  2. 2.
    Mishra, S., Pradhan, S.K., Rath, S.K.: Performance analysis of network intrusion detection system using back propagation for feed forward neural network in MATLAB/SIMULINK. Int. J. Comput. Eng. Res. 8(5), 58–65 (2018)Google Scholar
  3. 3.
    Borgohain, R.: FuGeIDS: fuzzy genetic paradigms in intrusion detection systems. Int. J. Adv. Netw. Appl. 3(6), 1409–1415 (2012)Google Scholar
  4. 4.
    Tajbakhsh, A., Rahmati, M., Mirzaei, A.: Intrusion detection using fuzzy association rules. Appl. Soft Comput. 9(2), 462–469 (2017)CrossRefGoogle Scholar
  5. 5.
    Gomez, J., Dasgupta, D.: Evolving fuzzy classifiers for intrusion detection. In: Proceeding of the 2002 IEEE, Workshop on Information Assurance, United States Military Academy, West Point, NY (2002)Google Scholar
  6. 6.
    Bhattacharjee, P.S., Begum, S.A.: Fuzzy approach for intrusion detection system: a survey. Int. J. Adv. Res. Comput. Sci. 4(2), 101–107 (2013)Google Scholar
  7. 7.
    Toosi, A.N., Kahani, M.: A new approach to intrusion detection based on an evolutionary soft computing model using neuro-fuzzy classifiers. Comput. Commun., 2201–2212 (2017). (Elsevier, Science Direct)CrossRefGoogle Scholar
  8. 8.
    Ishibuchi, H., Nakashima, T., Murata, T.: A fuzzy classifier system that generates fuzzy if–then rules for pattern classification problems. In: Proceedings of 2nd IEEE International Conference on Evolutionary Computation, vol. 2, pp. 759–764. IEEE, Perth, Australia, 29 Nov to 1 Dec 1995 (1995)Google Scholar
  9. 9.
    Suthishni, D.N.P., Kumar, G.P.R.: Intrusion detection analysis by implementing fuzzy logic. Int. J. Appl. Eng. Res. 11(5), 3216–3220 (2016)Google Scholar
  10. 10.
    Shanmugavadivu, R., Nagarajan, N.: Learning of intrusion detector in conceptual approach of fuzzy towards intrusion methodology. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 2(5), 246–250 (2012)Google Scholar
  11. 11.
    Haddadi, F., khanchi, S., Shetabi, M., Derhami, V.: Intrusion detection and attack classification using feedforward neural network. In: Second International Conference on Computer and Network Technology, 978-0-7695-4042-9/10 © 2010 IEEE, IEEE Computer Society, pp. 262–266.  https://doi.org/10.1109/iccnt.2010.28 (2010)
  12. 12.
    Shum, J., Malki, H.A.: Network intrusion detection system using neural network. In: Proceeding of IEEE Fourth International Conference on Natural Computation, pp. 242–246 (2008)Google Scholar
  13. 13.
    Wang, G., Hao, J., Ma, J., Huang, L.: A new approach to intrusion detection using artificial neural networks and fuzzy clustering. Expert Sys. Appl. 37(9), 6225–6232 (2010)CrossRefGoogle Scholar
  14. 14.
    Pandit, T., Dudy, A.: A feed forward artificial neural network based system to minimize Dos attack in wireless network. Int. J. Adv. Eng. Technol. 7(3), 938–947 (2014)Google Scholar
  15. 15.
    Nazir, A.: A comparative study of different artificial neural networks based intrusion detection systems. Int. J. Sci. Res. Publ. 3(7) (2013)Google Scholar
  16. 16.
    Pradhan, M., Pradhan, S.K., Sahu, S.K.: Anomaly detection using artificial neural network. Int. J. Eng. Sci. Emerg. Technol. (2012)Google Scholar
  17. 17.
    Patel, P.J., Shah, J.S., Patel, J.: Performance analysis of neural networks for intrusion detection system. Int. J. Comput. Technol. Appl. 8(2), 88–93 (2017)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Srinivas Mishra
    • 1
    Email author
  • Sateesh Kumar Pradhan
    • 2
  • Subhendu Kumar Rath
    • 3
  1. 1.Department of Computer Science & EngineeringBiju Patnaik University of TechnologyRourkelaIndia
  2. 2.Department of Computer ScienceUtkal UniversityBhubaneswarIndia
  3. 3.Biju Patnaik University of TechnologyRourkelaIndia

Personalised recommendations