ANOMALY DETECTION USING ARTIFICIAL NEURAL NETWORK

In this research, anomaly detection using neural network is introduced. This research aims to experiment with user behaviour as parameters in anomaly intrusion detection using a backpropagation neural network. Here we wanted to see if a neural network is able to classify normal traffic correctly, and detect known and unknown attacks without using a huge amount of training data. For the training and testing of the neural network, we used the DARPA Intrusion Detection Evaluation data sets. In our final experiment, we have got a classification rate of 88% on known and unknown attacks. Compared with other researches our result is very promising.

[1]  Deborah A. Frincke,et al.  Intrusion and Misuse Detection in Large-Scale Systems , 2002, IEEE Computer Graphics and Applications.

[2]  Sandeep Kumar,et al.  Classification and detection of computer intrusions , 1996 .

[3]  Giovanni Vigna,et al.  Intrusion detection: a brief history and overview , 2002 .

[4]  Lucas M. Venter,et al.  A comparison of Intrusion Detection systems , 2001, Comput. Secur..

[5]  Robert K. Cunningham,et al.  Improving Intrusion Detection Performance using Keyword Selection and Neural Networks , 2000, Recent Advances in Intrusion Detection.

[6]  Aurobindo Sundaram,et al.  An introduction to intrusion detection , 1996, CROS.

[7]  Chris Herringshaw,et al.  Detecting Attacks on Networks , 1997, Computer.

[8]  Anup K. Ghosh,et al.  A Study in Using Neural Networks for Anomaly and Misuse Detection , 1999, USENIX Security Symposium.

[9]  Hervé Debar,et al.  A neural network component for an intrusion detection system , 1992, Proceedings 1992 IEEE Computer Society Symposium on Research in Security and Privacy.