IDENTIFYING THREATS IN COMPUTER NETWORK BASED ON MULTILAYER NEURAL NETWORK
Journal Title: Наука та прогрес транспорту - Year 2018, Vol 0, Issue 2
Abstract
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.
Authors and Affiliations
I. V. Zhukovyts’kyy, V. M. Pakhomovа
SELECTION OF RATIONAL PARAMETERS OF THE NOMINAL MODE OF ELECTRIC LOCOMOTIVES
Purpose.The railways of Ukraine have been operated the locomotives, which are both morally and physically obsolete. Therefore, to ensure the competitiveness of rail transport it is necessary to update the locomotive flee...
ADVANTAGES OF RAPID METHOD FOR DETERMINING SCALE MASS AND DECARBURIZED LAYER OF ROLLED COIL STEEL
Purpose. To determine the universal empirical relationships that allow for operational calculation of scale mass and decarbonized layer depth based on the parameters of the technological process for rolled coil steel pro...
МЕТОД ПЛАНИРОВАНИЯ НЕДЕТЕРМИНИРОВАННЫХ ПРОЦЕССОВ ЭКСПЛУАТАЦИИ ПАРКА ЖЕЛЕЗНОДОРОЖНЫХ ТЕХНИЧЕСКИХ СИСТЕМ
Цель. Основной целью статьи является совершенствование автоматизированных систем эксплуатации парков железнодорожных технических систем – электродвигателей (ЭД) постоянного тока стрелочных переводов, с учетом факторов не...
CREATION OF EXPORT-ORIENTED NETWORK OF GRAIN ELEVATORS IN UKRAINE
Purpose. The scientific paper highlights improving the efficiency of export rail transportation of grain cargoes in Ukraine by introducing shipper routing and concentration of loading at the terminal grain elevators. Met...
ЖОРСТКІСТЬ ПРИКРІПЛЮВАЧІВ ПРОМІЖНИХ СКРІПЛЕНЬ ДЕРЕВ’ЯНИХ ШПАЛ ПРИ ДІЇ ГОРИЗОНТАЛЬНИХ ПОПЕРЕЧНИХ СИЛ
Мета. Незважаючи на постійне збільшення протяжності ділянок із безстиковою колією на залізобетонних шпалах, дерев’яні шпали – це один із варіантів підрейкових опор, що експлуатуються на достатньо великій кількості напрям...