Title :
Intrusion Detection Method Based on Sparse Neural Network
Author :
Huang, Weichun ; Ju, Lijuan
Author_Institution :
East China Jiao Tong Univ., Nanchang, China
Abstract :
The current network security technologies are mostly passive defense technology, but intrusion detection technology as an active and dynamic network security defense is a new direction in the development of network security technology and it is also a necessary complement to passive defense technology. In this paper, sparse neural network is applied to the field of intrusion detection. Sparse neural network simulates connected structure of the human brain, so it have advantages in shortening computing time, improving generalization ability and even reducing hardware implementation difficulty. Compared with intrusion detection method based on BP neural network, the detection rate by using intrusion detection method based on sparse neural network is higher.
Keywords :
backpropagation; computer network security; neural nets; BP neural network; detection rate; hardware implementation difficulty; intrusion detection method; intrusion detection technology; network security defense; network security technology; passive defense technology; sparse neural network; Artificial neural networks; Biological neural networks; Fault diagnosis; Humans; Intrusion detection; Neurons;
Conference_Titel :
Multimedia Technology (ICMT), 2010 International Conference on
Conference_Location :
Ningbo
Print_ISBN :
978-1-4244-7871-2
DOI :
10.1109/ICMULT.2010.5630912