Advertisement

Performance Analysis of NSL_KDD Data Set Using Neural Networks with Logistic Sigmoid Activation Unit

  • Vignendra JannelaEmail author
  • Sireesha Rodda
  • Shyam Nandan Reddy Uppuluru
  • Sai Charan Koratala
  • G. V. S. S. S. Chandra Mouli
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 77)

Abstract

Network intrusion detection system (NIDS) is a software tool that scans network traffic and performs security analysis on it. NIDS performs match operations upon passing traffic with a pre-established library of attacks in order to identify attacks or abnormal behavior. One of the standard data sets used widely for network intrusion systems is the NSL_KDD data set. The current paper aims to analyze the NSL_KDD data set using artificial neural network with sigmoid activation unit in order to perform a metric analysis study that is aimed at discovering the best fitting parameter values for optimal performance of the given data. Evaluation measures such as accuracy, F-measure, detection rate, and false alarm rate will be used to evaluate the efficiency of the developed model.

Keywords

Network intrusion detection system NSL_KDD Neural networks Logistic sigmoid activation unit 

Notes

Acknowledgements

This work is supported by the Science and Engineering Research Board (SERB), Ministry of Science & Technology, Govt. of India under Grant No. SB/FTP/ETA-0180/2014.

References

  1. 1.
    Revathi, S., Malathi, A.: A detailed analysis on NSL_KDD dataset using various machine learning techniques for intrusion detection. Int. J. Eng. Res. Technol. 2(12), 1–6 (2013)CrossRefGoogle Scholar
  2. 2.
    Aggarwal, P., Sharma, S.K.: Analysis of KDD dataset attributes—class wise for intrusion detection. In: 3rd International Conference on Recent Trends in Computing 2015 (ICRTC-2015)Google Scholar
  3. 3.
    Dreiseitl, S., Ohno-Machado, L.: Logistic regression and artificial neural network classification models: a methodology review. J. Biomed. Inform. 35, 352–359 (2002)CrossRefGoogle Scholar
  4. 4.
    Aziz, A.S.A., Azar, A.T., Hassanien, A.E, Hanafy, S.A.-O.: Continuous features discretization for anomaly intrusion detectors generation. In: Soft Computing in Industrial Applications, Volume 223 of the series Advances in Intelligent Systems and Computing, pp. 209–221Google Scholar
  5. 5.
    Hussain, J., Lalmuanawma, S.: Feature analysis, evaluation and comparisons of classification algorithms based on noisy intrusion dataset. In: 2nd International Conference on Intelligent, Computing, Communication & Convergence (ICCC-2016)Google Scholar
  6. 6.
    Singh, S., Bansal, M.: Improvement of intrusion detection system in data mining using neural network. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3(9),1124–1130Google Scholar
  7. 7.
    Tavallaee, M., Bagheri, E., Lu, W., Ghorbani, A.: A detailed analysis of the KDD CUP 99 data set. In: Second IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA) (2009, submitted)Google Scholar
  8. 8.
    McHugh, J.: Testing intrusion detection systems: a critique of the 1998 and 1999 DARPA intrusion detection system evaluations as performed by lincoln laboratory. ACM Trans. Inf. Syst. Secur. 3(4), 262–294 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Vignendra Jannela
    • 1
    Email author
  • Sireesha Rodda
    • 1
  • Shyam Nandan Reddy Uppuluru
    • 1
  • Sai Charan Koratala
    • 1
  • G. V. S. S. S. Chandra Mouli
    • 1
  1. 1.Department of Computer Science and Engineering, GITAM Institute of TechnologyGITAM UniversityVisakhapatnamIndia

Personalised recommendations