作者: Francisco José Mora-Gimeno , Francisco Maciá-Pérez , Iren Lorenzo-Fonseca , Juan Antonio Gil-Martínez-Abarca , Diego Marcos-Jorquera
DOI: 10.1007/978-3-642-21323-6_10
关键词:
摘要: The use of alert correlation methods in Distributed Intrusion Detection Systems (DIDS) has become an important process to address some the current problems this area. However, efficiency obtained is far from optimal results. This paper presents a novel approach based on integration multiple by using neural network Growing Neural Gas (GNG). Moreover, since systems have different detection capabilities, we modified learning algorithm positively weight best performing systems. results show validity proposal, both GNG and weighting efficiency.