System for detecting network anomalies using a hybrid of an uncontrolled and controlled neural network

- Kirichek, Galina (orcid.org/0000-0002-0405-7122), Harkusha, Vladyslav (orcid.org/0000-0001-5980-4802), Timenko, Artur (orcid.org/0000-0002-7871-4543) and Kulykovska, Nataliia (orcid.org/0000-0003-4691-5102) (2019) System for detecting network anomalies using a hybrid of an uncontrolled and controlled neural network Computer Science & Software Engineering : Proceedings of the 2nd Student Workshop (CS&SE@SW 2019), Kryvyi Rih, Ukraine, November 29, 2019 (2546). pp. 138-148. ISSN 1613-0073

Text paper09.pdf - Published Version Download (825kB)

Abstract

In this article realization method of attacks and anomalies detection with the use of training of ordinary and attacking packages, respectively. The method that was used to teach an attack on is a combination of an uncontrollable and controlled neural network. In an uncontrolled network, attacks are classified in smaller categories, taking into account their features and using the self- organized map. To manage clusters, a neural network based on back-propagation method used. We use PyBrain as the main framework for designing, developing and learning perceptron data. This framework has a sufficient number of solutions and algorithms for training, designing and testing various types of neural networks. Software architecture is presented using a procedural-object approach. Because there is no need to save intermediate result of the program (after learning entire perceptron is stored in the file), all the progress of learning is stored in the normal files on hard disk.

Item Type:	Article
Keywords:	neural network, learning, intrusion, anomalies detection, SOM
Subjects:	Science and knowledge. Organization. Computer science. Information. Documentation. Librarianship. Institutions. Publications > 00 Prolegomena. Fundamentals of knowledge and culture. Propaedeutics > 004 Computer science and technology. Computing. Data processing > 004.9 ІКТ ( Application-oriented computer-based techniques ) Science and knowledge. Organization. Computer science. Information. Documentation. Librarianship. Institutions. Publications > 3 Social Sciences > 37 Education > 378 Higher education. Universities. Academic study
Divisions:	Institute for Digitalisation of Education > Joint laboratory with SIHE “Kryvyi Rih National University”
Depositing User:	Сергій Олексійович Семеріков
Date Deposited:	24 Apr 2020 20:48
Last Modified:	24 Apr 2020 20:48
URI:	https://lib.iitta.gov.ua/id/eprint/720096

Downloads

Actions (login required)

View Item