Abstract
An Intrusion Detection System (IDS) is a system that monitors the network for identifying malicious activities. Upon identifying the unusual activities, IDS sends a notification to the network administrators to warn about the hackers' hostile activities. To detect intrusion, signature-based systems are considered to be one of the most effective methods. However, they cannot detect new attacks. Additionally, it is costly and challenging to keep the attack signatures database up to date with known signatures, which constructed a significant drawback. Neural networks are capable of learning through input patterns and have the potential to generalize data. In this paper, we propose a hybrid model based on Directed Batch Growing Self-Organizing Map (DBGSOM) combined with a Radial Basis Function Neural Network (RBFNN) detecting abnormalities in the network. Based on our experiment, the proposed model )performed well and has resulted in satisfactory performance measures compared to Self-Organizing Maps and Radial Basis Function Neural Network (SOM&RBFNN) model.