по
Journal Menu
> Issues > Rubrics > About journal > Authors > About the Journal > Requirements for publication > Editorial collegium > List of peer reviewers > Review procedure > Policy of publication. Aims & Scope. > Article retraction > Ethics > Legal information
Journals in science databases
About the Journal

В погоне за двумя зайцами поймай обоих сразу!
34 журнала издательства NOTA BENE входят одновременно и в ERIH PLUS, и в перечень изданий ВАК
При необходимости автору может быть предоставлена услуга срочной или сверхсрочной публикации!
MAIN PAGE > Back to contents
Neural network system of cyber-attacks detection on the basis of traffic analysis
Mustafaev Arslan Gasanovich

Doctor of Technical Science

Professor of the Department "Information technologies and information security" of the Dagestan State University of National Economy

367015, Russia, respublika Dagestan, g. Makhachkala, ul. Ataeva, 5, kab. 4.5

arslan_mustafaev@hotmail.com
Другие публикации этого автора
 

 

Abstract.

The author considers the methods of network attacks on a computer system detecting and reveals their advantages and drawbacks. The development of new methods and means of protection of computing systems from network attacks is urgent. The author considers the possibility of using artificial neural networks for traffic analysis. The author offers the neural network model of the incoming traffic filtration. The research is aimed at the creation of an adaptive neural network system serving as a cyber-attacks detection complex helping to take the peculiarities of the network traffic into consideration. To design the artificial neural network the author applies the Neural Network Toolbox pack from MATLAB 8.6 (R2015b). The author develops and offers the method of analysis of incoming traffic on the base of a three-layered neural network. The results of its teaching and testing demonstrate the possibility of its successful application for network cyber-attacks detection. The best results can be acquired in computing systems using the limited software suite allowing forming the traits of normal behavior for attacks detection more effectively. 

Keywords: computer network, network traffic, intrusion detection, error back propagation, multilayer perceptron, artificial neural network, classification, attacks detection, supervised learning, anomaly detection

DOI:

10.7256/2409-7543.2016.2.18834

Article was received:

18-04-2016


Review date:

18-04-2016


Publish date:

24-04-2016


This article written in Russian. You can find full text of article in Russian here .

References
1.
Goncharov V.A., Przhegorlinskii V.N. Metod obnaruzheniya setevykh atak, osnovannyi na klasternom analize vzaimodeistviya uzlov vychislitel'noi seti // Vestnik Ryazanskogo gosudarstvennogo radiotekhnicheskogo universiteta. 2011. № 36. C. 3-10.
2.
Hofmann A., Sick B. Evolutionary Optimization of Radial Basis Function Networks for Intrusion Detection. Proceedings, International Joint Conference on Neural Networks (Volume 1), 2003. p. 415-420.
3.
Middlemiss M., Dick G. Feature Selection of Intrusion detection data using a hybrid genetic of hybrid Intelligent systems. IOS Press Amsterdam, 2003. pp. 519-527.
4.
Kruglov V.V., Borisov V.V. Iskusstvennye neironnye seti. Teoriya i praktika. M.: Goryachaya liniya - Telekom, 2001. 382 s.
5.
Osovskii S. Neironnye seti dlya obrabotki informatsii. M.: Finansy i statistika, 2002. 344 s.
6.
KDD Cup 1999 Data [Elektronnyi resurs] http://kdd.ics.uci.edu/databases/kddcup99 (data obrashcheniya: 13.02.2016)
7.
Kayacik H.G., Zincir-Heywood A.N., Heywood M.I. Selecting Features for Intrusion Detection: A Feature Relevance Analysis on KDD 99 Intrusion Detection Datasets. Proceedings of the Third Annual Conference on Privacy, Security and Trust (PST-2005), October 2005.
8.
Mustafaev A.G. Primenenie iskusstvennykh neironnykh setei dlya rannei diagnostiki zabolevaniya sakharnym diabetom // Kibernetika i programmirovanie. 2016. № 2. S. 1-7. DOI: 10.7256/2306-4196.2016.2.17904. URL: http://e-notabene.ru/kp/article_17904.html
Link to this article

You can simply select and copy link from below text field.


Other our sites:
Official Website of NOTA BENE / Aurora Group s.r.o.
"History Illustrated" Website