Detection of threats propagation and data exflitration in corporate networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/27822 |
Resumo: | Modern corporations face nowadays multiple threats within their networks. In an era where companies are tightly dependent on information, these threats can seriously compromise the safety and integrity of sensitive data. Unauthorized access and illicit programs comprise a way of penetrating the corporate networks, able to traversing and propagating to other terminals across the private network, in search of confidential data and business secrets. The efficiency of traditional security defenses are being questioned with the number of data breaches occurred nowadays, being essential the development of new active monitoring systems with artificial intelligence capable to achieve almost perfect detection in very short time frames. However, network monitoring and storage of network activity records are restricted and limited by legal laws and privacy strategies, like encryption, aiming to protect the confidentiality of private parties. This dissertation proposes methodologies to infer behavior patterns and disclose anomalies from network traffic analysis, detecting slight variations compared with the normal profile. Bounded by network OSI layers 1 to 4, raw data are modeled in features, representing network observations, and posteriorly, processed by machine learning algorithms to classify network activity. Assuming the inevitability of a network terminal to be compromised, this work comprises two scenarios: a self-spreading force that propagates over internal network and a data exfiltration charge which dispatch confidential info to the public network. Although features and modeling processes have been tested for these two cases, it is a generic operation that can be used in more complex scenarios as well as in different domains. The last chapter describes the proof of concept scenario and how data was generated, along with some evaluation metrics to perceive the model’s performance. The tests manifested promising results, ranging from 96% to 99% for the propagation case and 86% to 97% regarding data exfiltration. |
id |
RCAP_683e849b69627b790894ea8c8cccd56f |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/27822 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Detection of threats propagation and data exflitration in corporate networksPattern recognitionBehavior analysisMachine learningNetwork monitoringNetwork activity classificationModern corporations face nowadays multiple threats within their networks. In an era where companies are tightly dependent on information, these threats can seriously compromise the safety and integrity of sensitive data. Unauthorized access and illicit programs comprise a way of penetrating the corporate networks, able to traversing and propagating to other terminals across the private network, in search of confidential data and business secrets. The efficiency of traditional security defenses are being questioned with the number of data breaches occurred nowadays, being essential the development of new active monitoring systems with artificial intelligence capable to achieve almost perfect detection in very short time frames. However, network monitoring and storage of network activity records are restricted and limited by legal laws and privacy strategies, like encryption, aiming to protect the confidentiality of private parties. This dissertation proposes methodologies to infer behavior patterns and disclose anomalies from network traffic analysis, detecting slight variations compared with the normal profile. Bounded by network OSI layers 1 to 4, raw data are modeled in features, representing network observations, and posteriorly, processed by machine learning algorithms to classify network activity. Assuming the inevitability of a network terminal to be compromised, this work comprises two scenarios: a self-spreading force that propagates over internal network and a data exfiltration charge which dispatch confidential info to the public network. Although features and modeling processes have been tested for these two cases, it is a generic operation that can be used in more complex scenarios as well as in different domains. The last chapter describes the proof of concept scenario and how data was generated, along with some evaluation metrics to perceive the model’s performance. The tests manifested promising results, ranging from 96% to 99% for the propagation case and 86% to 97% regarding data exfiltration.Nos dias de hoje, várias organizações enfrentam múltiplas ameaças no interior da sua rede. Numa época onde as empresas dependem cada vez mais da informação, estas ameaças podem compremeter seriamente a segurança e a integridade de dados confidenciais. O acesso não autorizado e o uso de programas ilícitos constituem uma forma de penetrar e ultrapassar as barreiras organizacionais, sendo capazes de propagarem-se para outros terminais presentes no interior da rede privada com o intuito de atingir dados confidenciais e segredos comerciais. A eficiência da segurança oferecida pelos sistemas de defesa tradicionais está a ser posta em causa devido ao elevado número de ataques de divulgação de dados sofridos pelas empresas. Desta forma, o desenvolvimento de novos sistemas de monitorização ativos usando inteligência artificial é crucial na medida de atingir uma deteção mais precisa em curtos períodos de tempo. No entanto, a monitorização e o armazenamento dos registos da atividade da rede são restritos e limitados por questões legais e estratégias de privacidade, como a cifra dos dados, visando proteger a confidencialidade das entidades. Esta dissertação propõe metodologias para inferir padrões de comportamento e revelar anomalias através da análise de tráfego que passa na rede, detetando pequenas variações em comparação com o perfil normal de atividade. Delimitado pelas camadas de rede OSI 1 a 4, os dados em bruto são modelados em features, representando observações de rede e, posteriormente, processados por algoritmos de machine learning para classificar a atividade de rede. Assumindo a inevitabilidade de um terminal ser comprometido, este trabalho compreende dois cenários: um ataque que se auto-propaga sobre a rede interna e uma tentativa de exfiltração de dados que envia informações para a rede pública. Embora os processos de criação de features e de modelação tenham sido testados para estes dois casos, é uma operação genérica que pode ser utilizada em cenários mais complexos, bem como em domínios diferentes. O último capítulo inclui uma prova de conceito e descreve o método de criação dos dados, com a utilização de algumas métricas de avaliação de forma a espelhar a performance do modelo. Os testes mostraram resultados promissores, variando entre 96% e 99% para o caso da propagação e entre 86% e 97% relativamente ao roubo de dados.2020-03-05T19:16:54Z2018-01-01T00:00:00Z2018info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/27822TID:202233898engOliveira, Miguel Filipeinfo: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:RCAAP2024-02-22T11:53:58Zoai:ria.ua.pt:10773/27822Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:00:33.544251Repositório 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 |
Detection of threats propagation and data exflitration in corporate networks |
title |
Detection of threats propagation and data exflitration in corporate networks |
spellingShingle |
Detection of threats propagation and data exflitration in corporate networks Oliveira, Miguel Filipe Pattern recognition Behavior analysis Machine learning Network monitoring Network activity classification |
title_short |
Detection of threats propagation and data exflitration in corporate networks |
title_full |
Detection of threats propagation and data exflitration in corporate networks |
title_fullStr |
Detection of threats propagation and data exflitration in corporate networks |
title_full_unstemmed |
Detection of threats propagation and data exflitration in corporate networks |
title_sort |
Detection of threats propagation and data exflitration in corporate networks |
author |
Oliveira, Miguel Filipe |
author_facet |
Oliveira, Miguel Filipe |
author_role |
author |
dc.contributor.author.fl_str_mv |
Oliveira, Miguel Filipe |
dc.subject.por.fl_str_mv |
Pattern recognition Behavior analysis Machine learning Network monitoring Network activity classification |
topic |
Pattern recognition Behavior analysis Machine learning Network monitoring Network activity classification |
description |
Modern corporations face nowadays multiple threats within their networks. In an era where companies are tightly dependent on information, these threats can seriously compromise the safety and integrity of sensitive data. Unauthorized access and illicit programs comprise a way of penetrating the corporate networks, able to traversing and propagating to other terminals across the private network, in search of confidential data and business secrets. The efficiency of traditional security defenses are being questioned with the number of data breaches occurred nowadays, being essential the development of new active monitoring systems with artificial intelligence capable to achieve almost perfect detection in very short time frames. However, network monitoring and storage of network activity records are restricted and limited by legal laws and privacy strategies, like encryption, aiming to protect the confidentiality of private parties. This dissertation proposes methodologies to infer behavior patterns and disclose anomalies from network traffic analysis, detecting slight variations compared with the normal profile. Bounded by network OSI layers 1 to 4, raw data are modeled in features, representing network observations, and posteriorly, processed by machine learning algorithms to classify network activity. Assuming the inevitability of a network terminal to be compromised, this work comprises two scenarios: a self-spreading force that propagates over internal network and a data exfiltration charge which dispatch confidential info to the public network. Although features and modeling processes have been tested for these two cases, it is a generic operation that can be used in more complex scenarios as well as in different domains. The last chapter describes the proof of concept scenario and how data was generated, along with some evaluation metrics to perceive the model’s performance. The tests manifested promising results, ranging from 96% to 99% for the propagation case and 86% to 97% regarding data exfiltration. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-01-01T00:00:00Z 2018 2020-03-05T19:16:54Z |
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/10773/27822 TID:202233898 |
url |
http://hdl.handle.net/10773/27822 |
identifier_str_mv |
TID:202233898 |
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_ |
1799137661060907008 |