ANOMALY NETWORK INTRUSION DETECTION SYSTEM BASED ON DISTRIBUTED TIME-DELAY NEURAL NETWORK (DTDNN)

Abstract

In this research, a hierarchical off-line anomaly network intrusion detection system based on Distributed Time-Delay Artificial Neural Network is introduced. This research aims to solve a hierarchical multi class problem in which the type of attack (DoS, U2R, R2L and Probe attack) detected by dynamic neural network. The results indicate that dynamic neural nets (Distributed Time-Delay Artificial Neural Network) can achieve a high detection rate, where the overall accuracy classification rate average is equal to 97.24%.

Keywords

• Anomaly
• Intrusion detection system
• Artificial neural network
• Distributed time-delay artificial neural network