DocumentCode :
2235571
Title :
Method of evolutionary neural network-based intrusion detection
Author :
Wang, Lina ; Yu, Ge ; Wang, Guoren ; Wang, Dong
Author_Institution :
Sch. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China
Volume :
5
fYear :
2001
fDate :
2001
Firstpage :
13
Abstract :
Intrusion detection is an important defence to protect the security of computer network systems. With an integrated technique of genetic algorithm and neural network, a method of evolutionary neural networks is proposed to perform intrusion detection in this paper. It is a robust enough, parallel and nonlinear dynamic processing system to satisfy requirements of real-time processing and prediction with high accuracy. With the new method, the structure of the neural network is optimized using a genetic algorithm. The obtained neural network model is thus used for intrusion detection and prealarm with high accuracy
Keywords :
authorisation; computer network management; genetic algorithms; nonlinear dynamical systems; parallel algorithms; real-time systems; telecommunication security; accurate prediction; computer network security; evolutionary neural network; genetic algorithm; intrusion detection; nonlinear dynamic system; prealarm; real-time processing; robust parallel processing; Accuracy; Computer networks; Computer security; Genetic algorithms; Intrusion detection; Neural networks; Nonlinear dynamical systems; Protection; Real time systems; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
Type :
conf
DOI :
10.1109/ICII.2001.983487
Filename :
983487
Link To Document :
بازگشت