Intrusion Detection System Using Optimum-Path Forest

Autor(es)

Pereira, Clayton ; Nakamura, Rodrigo ; Papa, Joao Paulo ; Costa, Kelton ; Pfeifer, T ; Jayasumana, A ; Aschenbruck, N

• Tipo de documento: Artigo Científico
• Fonte: 2011 IEEE 36TH CONFERENCE ON LOCAL COMPUTER NETWORKS (LCN); v. N/A, p. 4-pg., 2011-01-01.

Resumo

Intrusion detection systems that make use of artificial intelligence techniques in order to improve effectiveness have been actively pursued in the last decade. Neural networks and Support Vector Machines have been also extensively applied to this task. However, their complexity to learn new attacks has become very expensive, making them inviable for a real time retraining. In this research, we introduce a new pattern classifier named Optimum-Path Forest (OPF) to this task, which has demonstrated to be similar to the state-of-the-art pattern recognition techniques, but extremely more efficient for training patterns. Experiments on public datasets showed that OPF classifier may be a suitable tool to detect intrusions on computer networks, as well as allow the algorithm to learn new attacks faster than the other techniques. (AU)

• Processo FAPESP: 10/11676-7 - Redução do Tamanho do Conjunto de Treinamento por Floresta de Caminhos Ótimos e sua Aplicação em Máquinas de Vetores de Suporte
• Beneficiário: Rodrigo Yuji Mizobe Nakamura
• Modalidade de apoio: Bolsas no Brasil - Iniciação Científica
• Processo FAPESP: 09/16206-1 - Novas tendências em reconhecimento de padrões baseado em floresta de caminhos ótimos
• Beneficiário: João Paulo Papa
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores
• Processo FAPESP: 10/02045-3 - Detecção de Intrusões Baseada em Floresta de Caminhos Ótimos
• Beneficiário: Clayton Reginaldo Pereira
• Modalidade de apoio: Bolsas no Brasil - Mestrado