Science and Transport Progress
Published May 10, 2018 | Version v1
Journal article Open

IDENTIFYING THREATS IN COMPUTER NETWORK BASED ON MULTILAYER NEURAL NETWORK

Creators

  • 1. Dnipropetrovsk National University of Railway Transport named after Academician V. Lazaryan, Ukraine

Description

Purpose. Currently, there appear more often the reports of penetration into computer networks and attacks on the Web-server. Attacks are divided into the following categories: DoS, U2R, R2L, Probe. The purpose of the article is to identify threats in a computer network based on network traffic parameters using neural network technology, which will protect the server. Methodology. The detection of such threats as Back, Buffer_overflow, Quess_password, Ipsweep, Neptune in the computer network is implemented on the basis of analysis and processing of data on the parameters of network connections that use the TCP/IP protocol stack using the 19-1-25-5 neural network configuration in the Fann Explorer program. When simulating the operation of the neural network, a training (430 examples), a testing (200 examples) and a control sample (25 examples) were used, based on an open KDDCUP-99 database of 500000 connection records. Findings. The neural network created on the control sample determined an error of 0.322. It is determined that the configuration network 19-1-25-5 copes well with such attacks as Back, Buffer_overflow and Ipsweep. To detect the attacks of Quess_password and Neptune, the task of 19 network traffic parameters is not enough. Originality. We obtained dependencies of the neural network training time (number of epochs) on the number of neurons in the hidden layer (from 10 to 55) and the number of hidden layers (from 1 to 4). When the number of neurons in the hidden layer increases, the neural network by Batch algorithm is trained almost three times faster than the neural network by Resilient algorithm. When the number of hidden layers increases, the neural network by Resilient algorithm is trained almost twice as fast as that by Incremental algorithm. Practical value. Based on the network traffic parameters, the use of 19-1-25-5 configuration neural network will allow to detect in real time the computer network threats Back, Buffer_overflow, Quess_password, Ipsweep, Neptune and to perform appropriate monitoring.

Files

130797-Article Text-284825-1-10-20180529.pdf

Files (1.2 MB)

Name Size Download all
md5:28a44e524c7af3962e09bdf01a2969b1
1.2 MB Preview Download

Additional details

Related works

Is identical to
Journal article: http://stp.diit.edu.ua/article/view/130797 (URL)

References

  • Grishin, A. V. (2011). Neyrosetevye tekhnologii v zadachakh obnaruzheniya kompyuternykh atak. Informa-tsionnye tekhnologii i vychislitelnye sistemy, 1, 53-64. (in Ukranian).
  • Zhulkov, Y. V. (2007). Postroenie modulnykh neyronnykh setey dlya obnaruzheniya klassov setevykh atak (Dysertatsiia kandydata tekhnichnykh nauk). Peter the Great St. Petersburg Polytechnic University, Saint Petersburg. (in Russian)
  • Korpan, Y. V. (2015). Kompleks metodiv ta zasobiv zakhystu informatsii v kompiuternykh systemakh. Mir nauki i innovatsiy, 3, 31-35. (in Ukrainian)
  • Marchenko, A. A., Matvienko, S. V., & Nesteruk, F. G. (2007). Obnaruzhenie atak v sistemakh neyrosetevymi sredstvami. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 7(5), 83-93. (in English)
  • Pakhomоva, V. N. (2015). The possibilities of upgrading the computer network of information-telecommunication system of Dnieper railway. Informatsiino-keruiuchi systemy na zaliznychnomu transporti, 5, 32-38. (in Ukranian)
  • Piliugina, K. N. (2016). Artificial neural network approaches to intrusion detection. Modern Scientific Researches and Innovations, 2. Retrived from http://web.snauka.ru/issues/2016/02/63248 (in Russian)
  • Pisarenko, I. (2009). Neyrosetevye tekhnologii v bezopasnosti . Information Security, 4. Retrived from http://www.itsec.ru/articles2/Oborandteh/neyrosetevye-tehnologii-v-biznese (in Russian)
  • Postarnak, D. V. (2012). Kriticheskiy analiz modeley neyronnykh setey. Vestnik Tyumenskogo gosudarstvennogo universiteta. Fiziko-matematicheskie nauki. Informatika, 4, 162-167. (in Russian)
  • Amini, M., Rezaeenour, J., & Hadavandi, E. (2015). Effective Intrusion Detection with a Neural Network Ensemble using Fuzzy Clustering and Stacking Combination Method. Journal of Computing and Security, 1(4), 293-305. (in English)
  • Amini, M. A., Rezaeenour, J., & Hadavandi, E. (2016). Neural Network Ensemble Classifier for Effective Intrusion Detection using Fuzzy Clustering and Radial Basis Function Networks. International Journal on Artificial Intelligence Tools, 25 (02), 1550033. doi: 10.1142/s0218213015500335 (in English)
  • Hua Yang, Tao Li, Xinlei Hu, Feng Wang, & Yang Zou. (2014). A Survey of Artificial Immune System Based Intrusion Detection. The Scientific World Journal, 2014, 1-11. doi: 10.1155/2014/156790 (in English)
  • Branitskiy, A., & Kotenko, I. (2015). Network attack detection based on combination of neural, immune and neuro-fuzzy classifiers. The 18th IEEE Intern. Conf. on Computational Science and Engineering (IEEE CSE2015), 152-159. doi: 10.1109/cse.2015.26 (in English)
  • Cannady, J. (1998). Artificial Neural Networks for Misuse Detection. Proceedings of the 21st National Information Systems Security Conference (NISSC) (October 5–8, 1998), 443-456. (in English)
  • KDDCup1999Data (1999). Retrived from http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html. (in English)
  • Moradi, M. (2013). System for intrusion Detection and Classification of Attacks. Інформаційний портал університету Квінс. Retrived from http://research.cs.queensu.ca/moradi/148-04-mm-mz.pdf (in English)
  • Pakhomova, V. M. (2016). Network Traffic Forcasting in information-telecommunication System of Prydniprovsk Railways Based on Neuro-fuzzy Network. Science and Transport Progress, 6(66), 105-114. doi: 10.15802/stp2016/90485 (in English)