Quantum Growing Hierarchical Self Organized Map-Based Intrusion Detection System

Intrusion Detection is a critical process in network security. Neural networks approach is an advanced methodology used for intrusion detection. Self-organizing Maps (SOM) neural network is getting more attention in the field of intrusion detection. In this paper, a type of SOM - Quantum Growing Hierarchical Self Organized Map (QGHSOM) are made in order to improve the stability of intrusion detection and increase detection rate. The training process of QGHSOM networks can be described in terms of input pattern presentation and quantum states of weight update by quantum rotation gates. The QGHSOM is implemented and applied to the intrusion detection. The validities and feasibilities of the QGHSOM are confirmed through experiments on KDD Cup 99 datasets. The experiment result shows that the detection rate has been increased by employing the QGHSOM.