Identification of Programs Based on the Behavior

The algorithm of pattern mining from sequences of system calls is described. Patterns are used for process identification or establishing the fact that some sequence of system calls was produced by the process which was used in pattern extraction. Existing algorithms are computationaly more complex...

Full description

Bibliographic Details
Main Authors: M. V. Baklanovsky, A. R. Khanov
Format: Article
Language:English
Published: Yaroslavl State University 2014-12-01
Series:Моделирование и анализ информационных систем
Subjects:
Online Access:https://www.mais-journal.ru/jour/article/view/76
_version_ 1797877892029349888
author M. V. Baklanovsky
A. R. Khanov
author_facet M. V. Baklanovsky
A. R. Khanov
author_sort M. V. Baklanovsky
collection DOAJ
description The algorithm of pattern mining from sequences of system calls is described. Patterns are used for process identification or establishing the fact that some sequence of system calls was produced by the process which was used in pattern extraction. Existing algorithms are computationaly more complex or reveals high false positive runs in experiments in comparision with an automaton building algorithm. Our algorithm is less complex and more precise in comparision with the classical N-gram algorithm. Performance tests reveal that our kernel monitor does not significatly slow down the processing of the operating system. After 20 minutes of learning the algorithm is able to identify any thread of any process with 85% precision. Program identification based on behavior is used for anomaly detection of malicious activities in system.
first_indexed 2024-04-10T02:25:11Z
format Article
id doaj.art-a3b6a31cdd9f40d2ba894bdc1ac56731
institution Directory Open Access Journal
issn 1818-1015
2313-5417
language English
last_indexed 2024-04-10T02:25:11Z
publishDate 2014-12-01
publisher Yaroslavl State University
record_format Article
series Моделирование и анализ информационных систем
spelling doaj.art-a3b6a31cdd9f40d2ba894bdc1ac567312023-03-13T08:07:33ZengYaroslavl State UniversityМоделирование и анализ информационных систем1818-10152313-54172014-12-0121612013010.18255/1818-1015-2014-6-120-13070Identification of Programs Based on the BehaviorM. V. Baklanovsky0A. R. Khanov1Санкт-Петербургский государственный университетСанкт-Петербургский государственный университетThe algorithm of pattern mining from sequences of system calls is described. Patterns are used for process identification or establishing the fact that some sequence of system calls was produced by the process which was used in pattern extraction. Existing algorithms are computationaly more complex or reveals high false positive runs in experiments in comparision with an automaton building algorithm. Our algorithm is less complex and more precise in comparision with the classical N-gram algorithm. Performance tests reveal that our kernel monitor does not significatly slow down the processing of the operating system. After 20 minutes of learning the algorithm is able to identify any thread of any process with 85% precision. Program identification based on behavior is used for anomaly detection of malicious activities in system.https://www.mais-journal.ru/jour/article/view/76поведенческий анализаномальное обнаружениевыделение шаблонов
spellingShingle M. V. Baklanovsky
A. R. Khanov
Identification of Programs Based on the Behavior
Моделирование и анализ информационных систем
поведенческий анализ
аномальное обнаружение
выделение шаблонов
title Identification of Programs Based on the Behavior
title_full Identification of Programs Based on the Behavior
title_fullStr Identification of Programs Based on the Behavior
title_full_unstemmed Identification of Programs Based on the Behavior
title_short Identification of Programs Based on the Behavior
title_sort identification of programs based on the behavior
topic поведенческий анализ
аномальное обнаружение
выделение шаблонов
url https://www.mais-journal.ru/jour/article/view/76
work_keys_str_mv AT mvbaklanovsky identificationofprogramsbasedonthebehavior
AT arkhanov identificationofprogramsbasedonthebehavior