Title :
A New Intrusion Detection System Based on Multilayer Perceptrons Neural Network
Author :
Deng, Quan-cai ; Wang, Chun-dong ; CHang, Qing ; Wang, Huai-bin
Abstract :
In this paper, an intrusion detection model is proposed based on multilayer perceptrons neural network . In this model, HISTORY is used to collect data. Then, the data stream is converted its´ data structure for preprocessing. We use pattern matching module to filter out some of the known intrusions, in oder to reduce the load of the next step on intrusion detection, and the efficiency and accuracy of intrusion detection can be improved. The traditional single-packet inspection is powerless for the collaborative multi-packets intrusion, because it can only detect the intrusion which is an isolated incident. Therefore, Single-packet inspection with combining multi-packet detection method is proposed The experimental results show that: the multi-packet inspection can remedy the shortage of the single-packet inspection; the loss detection rate is reduced effectively. the efficiency of data processing has been improved by the analysis system of HISTORY.
Keywords :
data structures; multilayer perceptrons; pattern matching; security of data; data stream; data structure; intrusion detection system; multilayer perceptrons neural network; pattern matching module; Artificial neural networks; History; IP networks; Intrusion detection; Mathematical model; Sensitivity; Training;
Conference_Titel :
E-Product E-Service and E-Entertainment (ICEEE), 2010 International Conference on
Conference_Location :
Henan
Print_ISBN :
978-1-4244-7159-1
DOI :
10.1109/ICEEE.2010.5660667