Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Sistema de identificação de aplicações baseado em redes neuronais

Authors: Couto, Luís André Silva e;

Sistema de identificação de aplicações baseado em redes neuronais

Abstract

O trabalho que se apresenta pretende dar uma nova visão sobre as aplicações de Internet, mais especificamente aplicações de troca de ficheiros entre usuários (aplicações Peer-to-Peer). Devido a grande popularidade que este tipo de aplicações tem tido nos últimos anos, tornando-se uma enorme fatia do tráfego gerado na Internet, torna-se imprescindível a previsão e análise das reais necessidades que cada utilizador tem. Ao mesmo tempo têm evoluido as técnicas de camuflagem das aplicações Peer-to-Peer, desde mudando as portas de comunicação default, usar tráfego cifrado ou mesmo mudar as assinaturas das aplicações. Esta dissertação mostra uma nova perspectiva baseada em Redes Neuronais, possibilitando a identificação e análise do tráfego gerado por estas aplicações com taxas de sucesso muito grandes, apoiando-se apenas nos perfis de transmissão e recepção de dados que cada uma apresenta. Os resultados obtidos mostram que esta solução é válida, sendo capaz de apresentar taxas de sucesso muito elevadas, contornando os problemas das actuais técnicas de identificação de tráfego. ABSTRACT: The following work has the purpose to give a new vision about Internet applications, more specifically file-sharing applications between users (Peer-to- Peer). Due to a great popularity that these types of applications have gained in the past times, becoming an enormous fraction of generated traffic in the Internet, it’s essential to predict and analyze the real needs of each user. At the same time, camouflage techniques of Peer-to-Peer applications have evolved, changing default ports of communication, use of encrypted traffic or even changing signatures of applications. This dissertation shows a new approach based in Neural Networks, having the possibility the identification and analysis of the generated traffic by these applications with high success rates, supported only in traffic flows profiles. The results obtained show that this is a valid solution, which can be able to present elevated success rates, bypassing the actual techniques of traffic identification problems.

Mestrado em Engenharia Electrónica e Telecomunicações

Country
Portugal
Related Organizations
Keywords

Redes de comunicação de dados, Tráfego de redes, Redes neuronais, Engenharia electrónica

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    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
selected citations
These citations are derived from selected sources.
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
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!