Determining the Number of Hidden Neurons in a Multi Layer Feed Forward Neural Network

A neural network intrusion detection system (IDS) can be effective against network attacks. However, their effectiveness can be reduced by changes in the neural network architecture. One problem is determining the number of hidden layer neurons. This can lead to reduced detection and high failure rates. This paper describes the affects of architecture on the performance of IDSs while finding a means to choose the proper architecture and number of hidden neurons. This method reduces the need for trial and error in determining the number of hidden layer neurons in a multi layer feed forward neural network IDS.

[1]  Kõvanç Kõlõç,et al.  An easy approach for the selection of optimal neural network structure. , 2009 .

[2]  Akhilesh Swarup,et al.  Neural network approach for intrusion detection , 2009, ICIS.

[3]  Huiran Wang,et al.  Optimization of Neural Networks for Network Intrusion Detection , 2009, 2009 First International Workshop on Education Technology and Computer Science.

[4]  Zhang Wei,et al.  Intrusive Detection Systems Design based on BP Neural Network , 2010, 2010 Ninth International Symposium on Distributed Computing and Applications to Business, Engineering and Science.

[5]  Yacine Bouzida,et al.  Neural networks vs . decision trees for intrusion detection , 2006 .

[6]  Mehdi MORADI,et al.  A Neural Network Based System for Intrusion Detection and Classification of Attacks , 2004 .

[7]  Narges Arastouie,et al.  Backdoor Detection System Using Artificial Neural Network and Genetic Algorithm , 2011, 2011 International Conference on Computational and Information Sciences.

[8]  Kun Zhang,et al.  Intrusion Detection Based on RBF Neural Network , 2009, 2009 International Symposium on Information Engineering and Electronic Commerce.

[9]  Wenlong Fu,et al.  A Neural Network Based Intrusion Detection Data Fusion Model , 2010, 2010 Third International Joint Conference on Computational Science and Optimization.

[10]  Suhair Amer,et al.  Input Data Processing Techniques in Intrusion Detection Systems ? Short Review , 2010 .

[11]  Bi Jing,et al.  A New Method of Data Processing in the Intrusion Detection System with Neural Networks , 2010, 2010 Second International Workshop on Education Technology and Computer Science.

[12]  L. Ibrahim.  ANOMALY NETWORK INTRUSION DETECTION SYSTEM BASED ON DISTRIBUTED TIME-DELAY NEURAL NETWORK (DTDNN) , 2010 .

[13]  Tarun Bhaskar,et al.  A Hybrid Model for Network Security Systems: Integrating Intrusion Detection System with Survivability , 2008, Int. J. Netw. Secur..

[14]  Ingoo Han,et al.  The neural network models for IDS based on the asymmetric costs of false negative errors and false positive errors , 2003, Expert Syst. Appl..

[15]  Omar Zakaria,et al.  Identify Features and Parameters to Devise an Accurate Intrusion Detection System Using Artificial Neural Network , 2010 .

[16]  Abdullah Sharaf Alghamdi,et al.  Application of artificial neural network in detection of DOS attacks , 2009, SIN '09.