Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Обнаружение классов атак с использованием LSTM-сетей

выпускная квалификационная работа бакалавра

Обнаружение классов атак с использованием LSTM-сетей

Abstract

Тема выпускной квалификационной работы: «Обнаружение классов атак с использованием LSTM-сетей».Целью работы является обнаружение и классификация сетевых атак с использованием LSTM-сетей. Предметом исследования являются современные методы автоматизированного обнаружения сетевых атак. Задачи, решаемые в ходе исследования:Анализ набора данных и подготовка данных. Обучение LSTM сети для обнаружения и классификации сетевых атак. Оценка точности работы созданного средства. В ходе работы была исследована архитектура нейронной сети LSTM и структура набора данных UNSW-FB15. Были проанализированы современные исследования в области обнаружения сетевых атак.В результате работы было разработано средство обнаружения сетевых атак с помощью сети LSTM, была продемонстрирована эффективность средства. Был сделан вывод, что LSTM сеть отлично подходит для задачи обнаружения сетевых атак. Полученные результаты могут быть использованы в качестве основы для проектирования систем обнаружения сетевых атак.

The topic of the graduate qualification work is «Detection of attack classes using LSTM networks». The purpose of the study is detection and classification of network attacks using LSTM networks. The subject of the work is modern methods of automated detection of network attacks. The research set the following goals:Data set analysis and data preparation.LSTM network training for detecting and classifying network attacks.Evaluation of the accuracy of the created toolDuring the work the architecture of the LSTM neural network and the structure of the UNSW-FB15 dataset were studied. Modern studies in network attacks detection area were analyzed.The work resulted in development of a tool to detect network attacks using the LSTM network. Tool has satisfactory indicators in quality of network attacks detection. The studying point to conclusion that LSTM network is great for the task of detecting network attacks.The results could be used as a base for network attack detection systems designing.

Keywords

principal component analysis, classification of attacks, recurrent neural networks, классификация атак, LSTM, рекуррентные нейронные сети, метод Ð³Ð»Ð°Ð²Ð½Ñ‹Ñ ÐºÐ¾Ð¼Ð¿Ð¾Ð½ÐµÐ½Ñ‚

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author? Do you have the OA version of this publication?