Browsing by Author "Zhukovyts’kyy, Igor V."

Now showing 1 - 5 of 5

Detection of Attacks on a Computer Network Based on the Use of Neural Networks Complex
(Дніпровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпро, 2020) Zhukovyts’kyy, Igor V.; Pakhomova, Victoria M.; Ostapets, Denis O.; Tsyhanok, O. I.
ENG: Purpose. The article is aimed at the development of a methodology for detecting attacks on a computer network. To achieve this goal the following tasks were solved: to develop a methodology for detecting attacks on a computer network based on an ensemble of neural networks using normalized data from the open KDD Cup 99 database; when performing machine training to identify the optimal parameters of the neural network which will provide a sufficiently high level of reliability of detection of intrusions into the computer network. Methodology. As an architectural solution of the attack detection module, a two-level network system is proposed, based on an ensemble of five neural networks of the multilayer perceptron type. The first neural network to determine the category of attack class (DoS, R2L, U2R, Probe) or the fact that there was no attack; other neural networks – to detect the type of attack, if any (each of these four neural networks corresponds to one class of attack and is able to identify types that belong only to this class). Findings. The created software model was used to study the parameters of the neural network configuration 41–1–132–5, which determines the category of the attack class on the computer network. It is determined that the optimal training speed is 0.001. The ADAM algorithm proved to be the best for optimization. The ReLU function is the most suitable activation function for the hidden layer, and the hyperbolic tangent function – for the output layer activation function. Accuracy in test and validation samples was 92.86 % and 91.03 %, respectively. Originality. The developed software model, which uses the Python 3.5 programming lan-guage, the integrated development environment PyCharm 2016.3 and the Tensorflow 1.2 framework, makes it pos-sible to detect all types of attacks of DoS, U2R, R2L, Probe classes. Practical value. Graphical dependencies of accuracy of neural networks at various parameters are received: speed of training; activation function; optimization algorithm. The optimal parameters of neural networks have been determined, which will ensure a sufficiently high level of reliability of intrusion detection into a computer network.
Development of a Self-Diagnostics Subsystem of the Information-Measuring System Using Anfis Controllers
(НВП ПП «Технологічний центр», 2018) Zhukovyts’kyy, Igor V.; Kliushnyk, Ihor A.
EN: A hybrid self-diagnostic system was designed to evaluate correctness of functioning of sensors of the information-measuring system of testing hydraulic transmissions of diesel locomotives of UHP 750 type. The system features the possibility of checking certain four parameters in steady-state operation conditions using known mathematical dependencies. For the other 14 parameters (for which mathematical dependencies were not studied and which have a high complexity of calculations), 14 neural-fuzzy ANFIS networks were developed. Self-diagnostic algorithms using ANFIS controllers were elaborated. The algorithms provide prediction of individual system parameters with the help of ANFIS controllers and a further comparison of the predicted parameters with the measured parameters. The ANFIS controller structure with the proposed Sugeno rule set was constructed and its efficiency was shown. Network training and test of the diagnostic subsystem were performed using the data sets obtained in a series of tests of hydraulic transmissions conducted at Promteplovoz diesel locomotive repair plant. The test results have shown that application of the proposed procedure ensures obtaining of correct result of the self-diagnostic subsystem operation.
Identifying Threats in Computer Network Based on Multilayer Neural Network
(Дніпропетровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпро, 2018) Zhukovyts’kyy, Igor V.; Pakhomova, Victoria M.
ENG: 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.
Research of Token Ring Network Options in Automation System of Marshalling Yard
(Politechnika Slaska, Poland, 2018) Zhukovyts’kyy, Igor V.; Pakhomova, Victoria N.
ENG: In the automation systems of sorting process the use of computer networks of Ethernet technology is possible. But its traditional drawback is a probabilistic nature of the network access, which does not guarantee the information transmission in specified time intervals. However, there are other technologies that are free from this defect, for example, the Token Ring technology. A methodology, for determination of the network parameters in the automation system on marshalling yard at the restriction of the average time for application waiting in the queue at the station network has worked out. Using the token method of access to the ring, the state diagram of network stations was compiled. This is the basis for simulation model of the Token Ring network, which was developed in the GPSS environment. As a result of simulation the dependencies of the maximum queue length at the network station on the frame length, intensity, and distribution of time for application receipt from the station were obtained.
Use of an Automaton Model for the Designing of Real-Time Information Systems in the Railway Stations
(The Silesian University of Technology, Katowice, Poland, 2017) Zhukovyts’kyy, Igor V.
EN: To display the information on technological processes at railway stations it is proposed to develop the special models built on the basis of finite state machine Mealy. The input alphabet of such machines is represented by the real signals (from the floor equipment, the related information systems and the dispatch office personnel). This representation allows one to formalize the software design process of real-time information management systems for these technological processes. The article demonstrates the possibility of formal transition from the automaton model to the software algorithms. The proposed approach was tested when designing the information system for Nizhnedneprovsk junction railway yard.