Detection of side channel attacks at the network physical layer
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/31363 |
Resumo: | Today, with the advent of IoT and the resulting fragmentation of wireless technologies, they bring not only benefits, but also concerns. Daily, several individuals communicate with each other using various communication methods. Individuals use a variety of devices for innocuous day-to-day activities; however, there are some malicious individuals (dishonest agents) whose aim is to cause harm, with the exfiltration of information being one of the biggest concerns. Since the security of Wi-Fi communications is one of the areas of greatest investment and research regarding Internet security, dishonest agents make use of side channels to exfiltrate information, namely Bluetooth. Most current solutions for anomaly detection on networks are based on analyzing frames or packets, which, inadvertently, can reveal user behavior patterns, which they consider to be private. In addition, solutions that focus on inspecting physical layer data typically use received signal power (RSSI) as a distance metric and detect anomalies based on the relative position of the network nodes, or use the spectrum values directly on models classification without prior data processing. This Dissertation proposes mechanisms to detect anomalies, while ensuring the privacy of its nodes, which are based on the analysis of radio activity in the physical layer, measuring the behavior of the network through the number of active and inactive frequencies and the duration of periods of silence and activity. After the extraction of properties that characterize these metrics,an exploration and study of the data is carried out, followed by the use of the result to train One-Class Classification models. The models are trained with data taken from a series of interactions between a computer, an AP, and a mobile phone in an environment with reduced noise, in an attempt to simulate a simplified home automation scenario. Then, the models were tested with similar data but containing a compromised node, which periodically sent a file to a local machine via a Bluetooth connection. The data show that, in both situations, it was possible to achieve detection accuracy rates in the order of 75 % and 99 %. This work ends with some ideas of resource work, namely changes in the level of pre-processing, ideas of new tests and how to reduce the percentage of false negatives. |
id |
RCAP_e707faab5cac66a488b147e60aed7f02 |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/31363 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Detection of side channel attacks at the network physical layerSide-channelsNetwork monitoringRadio signal monitoringAnomaly detectionOne-class classificationMachine learningToday, with the advent of IoT and the resulting fragmentation of wireless technologies, they bring not only benefits, but also concerns. Daily, several individuals communicate with each other using various communication methods. Individuals use a variety of devices for innocuous day-to-day activities; however, there are some malicious individuals (dishonest agents) whose aim is to cause harm, with the exfiltration of information being one of the biggest concerns. Since the security of Wi-Fi communications is one of the areas of greatest investment and research regarding Internet security, dishonest agents make use of side channels to exfiltrate information, namely Bluetooth. Most current solutions for anomaly detection on networks are based on analyzing frames or packets, which, inadvertently, can reveal user behavior patterns, which they consider to be private. In addition, solutions that focus on inspecting physical layer data typically use received signal power (RSSI) as a distance metric and detect anomalies based on the relative position of the network nodes, or use the spectrum values directly on models classification without prior data processing. This Dissertation proposes mechanisms to detect anomalies, while ensuring the privacy of its nodes, which are based on the analysis of radio activity in the physical layer, measuring the behavior of the network through the number of active and inactive frequencies and the duration of periods of silence and activity. After the extraction of properties that characterize these metrics,an exploration and study of the data is carried out, followed by the use of the result to train One-Class Classification models. The models are trained with data taken from a series of interactions between a computer, an AP, and a mobile phone in an environment with reduced noise, in an attempt to simulate a simplified home automation scenario. Then, the models were tested with similar data but containing a compromised node, which periodically sent a file to a local machine via a Bluetooth connection. The data show that, in both situations, it was possible to achieve detection accuracy rates in the order of 75 % and 99 %. This work ends with some ideas of resource work, namely changes in the level of pre-processing, ideas of new tests and how to reduce the percentage of false negatives.Hoje, com o advento da IoT e a resultante fragmentação das tecnologias sem fio, elas trazem não apenas benefícios, mas também preocupações. Diariamente vários indivíduos se comunicam entre si usando vários métodos de comunicação. Os indivíduos usam uma variedade de dispositivos para atividades inócuas do dia-adia; no entanto, existem alguns indivíduos mal-intencionados (agentes desonestos) cujo objetivo é causar danos, sendo a exfiltração de informação uma das maiores preocupações. Sendo a segurança das comunicações Wi-Fi uma das áreas de maior investimento e investigação no que toca a segurança na Internet, os agentes desonestos fazem uso de canais laterais para exfiltrar informação, nomeadamente o Bluetooth. A maioria das soluções atuais para deteção de anomalias em redes baseiam-se em analisar tramas ou pacotes, o que, inadvertidamente, pode revelar padrões de comportamento dos utilizadores, que estes considerem privados. Além disso, as soluções que se focam em inspecionar dados da camada física normalmente usam a potência de sinal recebido (RSSI) como uma métrica de distância e detetam anomalias baseadas na posição relativa dos nós da rede, ou usam os valores do espetro diretamente em modelos de classificação sem prévio tratamento de dados. Esta Dissertação propõe mecanismos para deteção de anomalias, assegurando simultaneamente a privacidade dos seus nós, que se baseiam na análise de atividade rádio na camada física, medindo os comportamentos da rede através do número de frequências ativas e inativas e a duração de períodos de silêncio e atividade. Depois da extração de propriedades que caracterizam estas métricas, é realizada uma exploração dos dados e um estudo das mesmas, sendo depois usadas para treinar modelos de classificação mono-classe. Os modelos são treinados com dados retirados de uma série de interações entre um computador, um AP, e um telemóvel num ambiente com ruído reduzido, numa tentativa de simular um cenário de automação doméstica simplificado. De seguida, os modelos foram testados com dados semelhantes mas contendo um nó comprometido, que periodicamente enviava um ficheiro para uma máquina local através de uma ligação Bluetooth. Os dados mostram que, em ambas as situações, foi possível atingir taxas de precisão de deteção na ordem dos 75% e 99%. Este trabalho finaliza com algumas ideias de trabalho futuro, nomeadamente alterações ao nível do pré-processamento, ideias de novos testes e como diminuir a percentagem de falsos negativos.2021-05-13T14:20:44Z2021-02-22T00:00:00Z2021-02-22info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/31363engCoelho, Daniel Martinsinfo: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:RCAAP2024-02-22T12:00:33Zoai:ria.ua.pt:10773/31363Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:03:16.202698Repositório 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 side channel attacks at the network physical layer |
title |
Detection of side channel attacks at the network physical layer |
spellingShingle |
Detection of side channel attacks at the network physical layer Coelho, Daniel Martins Side-channels Network monitoring Radio signal monitoring Anomaly detection One-class classification Machine learning |
title_short |
Detection of side channel attacks at the network physical layer |
title_full |
Detection of side channel attacks at the network physical layer |
title_fullStr |
Detection of side channel attacks at the network physical layer |
title_full_unstemmed |
Detection of side channel attacks at the network physical layer |
title_sort |
Detection of side channel attacks at the network physical layer |
author |
Coelho, Daniel Martins |
author_facet |
Coelho, Daniel Martins |
author_role |
author |
dc.contributor.author.fl_str_mv |
Coelho, Daniel Martins |
dc.subject.por.fl_str_mv |
Side-channels Network monitoring Radio signal monitoring Anomaly detection One-class classification Machine learning |
topic |
Side-channels Network monitoring Radio signal monitoring Anomaly detection One-class classification Machine learning |
description |
Today, with the advent of IoT and the resulting fragmentation of wireless technologies, they bring not only benefits, but also concerns. Daily, several individuals communicate with each other using various communication methods. Individuals use a variety of devices for innocuous day-to-day activities; however, there are some malicious individuals (dishonest agents) whose aim is to cause harm, with the exfiltration of information being one of the biggest concerns. Since the security of Wi-Fi communications is one of the areas of greatest investment and research regarding Internet security, dishonest agents make use of side channels to exfiltrate information, namely Bluetooth. Most current solutions for anomaly detection on networks are based on analyzing frames or packets, which, inadvertently, can reveal user behavior patterns, which they consider to be private. In addition, solutions that focus on inspecting physical layer data typically use received signal power (RSSI) as a distance metric and detect anomalies based on the relative position of the network nodes, or use the spectrum values directly on models classification without prior data processing. This Dissertation proposes mechanisms to detect anomalies, while ensuring the privacy of its nodes, which are based on the analysis of radio activity in the physical layer, measuring the behavior of the network through the number of active and inactive frequencies and the duration of periods of silence and activity. After the extraction of properties that characterize these metrics,an exploration and study of the data is carried out, followed by the use of the result to train One-Class Classification models. The models are trained with data taken from a series of interactions between a computer, an AP, and a mobile phone in an environment with reduced noise, in an attempt to simulate a simplified home automation scenario. Then, the models were tested with similar data but containing a compromised node, which periodically sent a file to a local machine via a Bluetooth connection. The data show that, in both situations, it was possible to achieve detection accuracy rates in the order of 75 % and 99 %. This work ends with some ideas of resource work, namely changes in the level of pre-processing, ideas of new tests and how to reduce the percentage of false negatives. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-05-13T14:20:44Z 2021-02-22T00:00:00Z 2021-02-22 |
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/10773/31363 |
url |
http://hdl.handle.net/10773/31363 |
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_ |
1799137687755554816 |