Download now Free registration required
In this paper, the authors proposed a new approach to design the system using a hybrid of misuse and anomaly detection for training of normal and attack packets respectively. The utilized method for attack training is the combination of unsupervised and supervised Neural Network (NN) for Intrusion Detection System. By the unsupervised NN based on Self Organizing Map (SOM), attacks will be classified into smaller categories considering their similar features and then unsupervised NN based on backpropagation will be used for clustering. By misuse approach known packets would be identified fast and unknown attacks will be able to detect by this method.
- Format: PDF
- Size: 195.9 KB