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 ÑÐµÑ‚ÐµÐ²Ñ‹Ñ Ð°Ñ‚Ð°Ðº методом обучения с подкреплением

выпускная квалификационная работа бакалавра

Обнаружение ÑÐµÑ‚ÐµÐ²Ñ‹Ñ Ð°Ñ‚Ð°Ðº методом обучения с подкреплением

Abstract

Тема выпускной квалификационной работы: «Обнаружение сетевых атак методом обучения с подкреплением». Целью работы является выявление вредоносного трафика среди потока сетевых пакетов при помощи нейронной сети, использующей архитектуру обучения с подкреплением. Предметом исследования являются современные методы фильтрации сетевых пакетов. Задачи, решаемые в ходе исследования:Исследование проблемы обнаружения сетевых атак. Изучение особенностей архитектуры обучения с подкреплением. Программная реализация метода выявления сетевых атак в заданном датасете с применением нейронной сети, использующей архитектуру обучения с подкреплением. Оценка скорости и точности работы созданного средства. В ходе работы был исследован общий алгоритм архитектуры обучения с подкреплением. Кроме того, были проанализированы современные исследования в области обеспечения безопасности передачи данных через сеть. В результате работы было реализовано средство выявления вредоносного трафика, затем была продемонстрирована эффективность средства. Был сделан вывод, что безопасность сетевого стека может быть усилена по сравнению с имеющимся на данный момент уровнем защиты. Полученные результаты могут быть использованы в качестве основы для проектирования средств динамического анализа сетевого трафика.

Topic of the final qualification work: "Attack detection by reinforcement learning". The purpose of the work is to detect malicious traffic among packet streams using a neural network using a reinforcement learning architecture. The subject of the research is modern methods of packet filtering. Tasks to be solved during the study:Study of the problems of identifying the network attacks. Features of the structure with reinforcement learning. Development of a method for detecting attacks at a given date using a neural network using reinforcement learning architecture. Software implementation of the developed method. Evaluation of the speed and accuracy of the created tool. In the course of the work, the general algorithm of the architecture of reinforcement learning was investigated. In addition, modern research in the field of data transmission security through the network was analyzed. The work resulted in development of a tool to detecting malicious traffic. Tool has satisfactory indicators in not only quantitative defect detection, but also in productivity. The studying point to conclusion that network stack security is poorly examined. The results could be used as a base for dynamic analysis network traffic.

Keywords

reinforcement learning, vulnerability scanning, cетевые атаки, обучение с подкреплением, искусственный интеллект, network attacks, network traffic recognition, поиск уязвимостей, artificial intelligence, распознание трафика

  • 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
Related to Research communities
Upload OA version
Are you the author? Do you have the OA version of this publication?