Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks

Detalhes bibliográficos
Autor(a) principal: Pinho, Pedro Miguel Pinto e
Data de Publicação: 2012
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.6/3752
Resumo: Nowadays, communications through computer networks are of utmost importance for the normal functioning of organizations, worldwide transactions and content delivery. These networks are threatened by all kinds of attacks, leading to traffic anomalies that will eventually disrupt the normal behaviour of the networks, exploring specific breaches on a system component or exhausting network resources. Automatic detection of these network anomalies comprises one of the most important resources for network administration, and Intrusion Detection Systems(IDSs) are amongst the systems responsible for this automatic detection. This dissertation starts from the assumption that it is possible to use machine learning to, consistently and automatically, produce rules for an intrusion detector based on statistics for the first 64 bytes of the headers of Internet Protocol (IP) packets. The survey on the state of the art on related works and currently available IDSs shows that the specific approach taken here is worth to be explored. The decision tree learning algorithm known as C4.5 is identified as a suitable means to produce the aforementioned rules, due to the similarity between their syntax and the tree structure. Several rules are then devised using the ML approach for several attacks. The attacks were the same used in a previous work, in which the rules were devised manually. Both rule sets are then compared to show that, in fact, it is possible to construct rules using the approach taken herein, and that the rules created resorting to the C4.5 algorithm are superior to the ones devised after thorough human analysis of several statistics calculated for the bytes of the headers of the packets. To compare them, each rule set was used to detect intrusions in third party traces containing attacks and in live traffic during simulation of attacks. Most of the attacks producing noticeable impact on the headers were detected by both rule sets, but the results for the third party traces were better in the case of the ML devised rules, providing a clear evidence for the aforementioned assumptions.
id RCAP_6d9ebf50994d65fc43f140dedda59cdf
oai_identifier_str oai:ubibliorum.ubi.pt:10400.6/3752
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networksInformática - Aprendizagem automáticaInformática - Captura de tráfegoInformática - Deteção de intrusõesInformática - Tráfego de redeInformática - Ficheiros de captura etiquetadosNowadays, communications through computer networks are of utmost importance for the normal functioning of organizations, worldwide transactions and content delivery. These networks are threatened by all kinds of attacks, leading to traffic anomalies that will eventually disrupt the normal behaviour of the networks, exploring specific breaches on a system component or exhausting network resources. Automatic detection of these network anomalies comprises one of the most important resources for network administration, and Intrusion Detection Systems(IDSs) are amongst the systems responsible for this automatic detection. This dissertation starts from the assumption that it is possible to use machine learning to, consistently and automatically, produce rules for an intrusion detector based on statistics for the first 64 bytes of the headers of Internet Protocol (IP) packets. The survey on the state of the art on related works and currently available IDSs shows that the specific approach taken here is worth to be explored. The decision tree learning algorithm known as C4.5 is identified as a suitable means to produce the aforementioned rules, due to the similarity between their syntax and the tree structure. Several rules are then devised using the ML approach for several attacks. The attacks were the same used in a previous work, in which the rules were devised manually. Both rule sets are then compared to show that, in fact, it is possible to construct rules using the approach taken herein, and that the rules created resorting to the C4.5 algorithm are superior to the ones devised after thorough human analysis of several statistics calculated for the bytes of the headers of the packets. To compare them, each rule set was used to detect intrusions in third party traces containing attacks and in live traffic during simulation of attacks. Most of the attacks producing noticeable impact on the headers were detected by both rule sets, but the results for the third party traces were better in the case of the ML devised rules, providing a clear evidence for the aforementioned assumptions.Hoje em dia, as comunicações através de redes informáticas são da maior importância para o normal funcionamento das organizações, transações mundiais e entrega de conteúdos. Essas redes são ameaçadas por todo o tipo de ataques, levando a anomalias no tráfego, que eventualmente vão corromper o normal funcionamento da rede, explorando falhas específicas num componente de um sistema, ou esgotando os recursos de rede. A deteção automática dessas anomalias de rede é um dos recursos mais importantes para os administradores de rede, e os Sistemas de Deteção de Intrusões estão entre os sistemas responsáveis por essa deteção. Esta dissertação tem como ponto de partida, a assunção que é possível usar mecanismos de aprendizagem automática para produzir, de modo consistente e automático, regras para a deteção de intrusões, baseadas em estatísticas dos primeiros 64 bytes dos cabeçalhos dos pacotes IP. O estudo sobre o estado da arte em trabalhos da área, e em sistemas de deteção atualmente disponíveis, mostrou que o método usado nesta dissertação merece ser estudado. O algoritmo de árvores de decisão C4.5 foi identificado como um meio apropriado para produzir as regras já referidas, devido à semelhança entre a sintaxe das mesmas e a estrutura em árvore deste algoritmo. Várias regras foram depois produzidas para vários tipos de ataque, usando a abordagem por aprendizagem automática. Os ataques tomados em consideração foram os mesmos que foram utilizados num trabalho anterior, em que a regras foram concebidas manualmente. Ambos os conjuntos de regras são depois comparados, para mostrar que, de facto, é possível construir regras através da abordagem utilizada nesta dissertação, e que as regras criadas através do algoritmo C4.5 são superiores às que foram criadas através de análise humana das várias estatísticas calculadas para os bytes dos cabeçalhos dos pacotes. Para as comparar, cada conjunto de regras foi utilizado para detetar intrusões em registos de tráfego disponíveis na Internet contendo ataques e em tráfego em tempo real, durante a simulação de ataques. A maioria dos ataques que produz um forte impacto nos cabeçalhos dos pacotes foi detetado por ambos os conjuntos, mas os resultados com os registos retirados da Internet foram melhores para as regras produzidas por aprendizagem automática, dando uma prova clara para o que foi previamente assumido.Inácio, Pedro Ricardo MoraisuBibliorumPinho, Pedro Miguel Pinto e2015-07-21T15:06:06Z20122012-102012-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.6/3752enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-12-15T09:40:15Zoai:ubibliorum.ubi.pt:10400.6/3752Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:45:06.909235Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
title Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
spellingShingle Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
Pinho, Pedro Miguel Pinto e
Informática - Aprendizagem automática
Informática - Captura de tráfego
Informática - Deteção de intrusões
Informática - Tráfego de rede
Informática - Ficheiros de captura etiquetados
title_short Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
title_full Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
title_fullStr Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
title_full_unstemmed Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
title_sort Intrusion detection based on behavioral rules for the bytes of the headers of the data units in IP networks
author Pinho, Pedro Miguel Pinto e
author_facet Pinho, Pedro Miguel Pinto e
author_role author
dc.contributor.none.fl_str_mv Inácio, Pedro Ricardo Morais
uBibliorum
dc.contributor.author.fl_str_mv Pinho, Pedro Miguel Pinto e
dc.subject.por.fl_str_mv Informática - Aprendizagem automática
Informática - Captura de tráfego
Informática - Deteção de intrusões
Informática - Tráfego de rede
Informática - Ficheiros de captura etiquetados
topic Informática - Aprendizagem automática
Informática - Captura de tráfego
Informática - Deteção de intrusões
Informática - Tráfego de rede
Informática - Ficheiros de captura etiquetados
description Nowadays, communications through computer networks are of utmost importance for the normal functioning of organizations, worldwide transactions and content delivery. These networks are threatened by all kinds of attacks, leading to traffic anomalies that will eventually disrupt the normal behaviour of the networks, exploring specific breaches on a system component or exhausting network resources. Automatic detection of these network anomalies comprises one of the most important resources for network administration, and Intrusion Detection Systems(IDSs) are amongst the systems responsible for this automatic detection. This dissertation starts from the assumption that it is possible to use machine learning to, consistently and automatically, produce rules for an intrusion detector based on statistics for the first 64 bytes of the headers of Internet Protocol (IP) packets. The survey on the state of the art on related works and currently available IDSs shows that the specific approach taken here is worth to be explored. The decision tree learning algorithm known as C4.5 is identified as a suitable means to produce the aforementioned rules, due to the similarity between their syntax and the tree structure. Several rules are then devised using the ML approach for several attacks. The attacks were the same used in a previous work, in which the rules were devised manually. Both rule sets are then compared to show that, in fact, it is possible to construct rules using the approach taken herein, and that the rules created resorting to the C4.5 algorithm are superior to the ones devised after thorough human analysis of several statistics calculated for the bytes of the headers of the packets. To compare them, each rule set was used to detect intrusions in third party traces containing attacks and in live traffic during simulation of attacks. Most of the attacks producing noticeable impact on the headers were detected by both rule sets, but the results for the third party traces were better in the case of the ML devised rules, providing a clear evidence for the aforementioned assumptions.
publishDate 2012
dc.date.none.fl_str_mv 2012
2012-10
2012-01-01T00:00:00Z
2015-07-21T15:06:06Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.6/3752
url http://hdl.handle.net/10400.6/3752
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799136347533869056