DEEP LEARNING SYSTEM TO INTRUSION DETECTION BASED ON RECURRENT NEURAL NETWORK

Abstract: Recently, the huge amounts of data and its incremental increase have changed the importance of information security and data analysis systems. Intrusion detection system (IDS) is a system that monitors and analyzes data to detect any intrusion in the system or network. High volume, variety and high speed of data generated in the network have made the data analysis process to detect attacks by traditional techniques very difficult. To proposed Recurrent Neural Network (RNN) algorithm to detect the IDS. The data processed by the preprocessing module are compressed by the auto-encoder module to obtain a lower-dimensional reconstruction feature, and the classification result is obtained through the classification module. Compressed features of each traffic are stored in the database module which can both provide retraining and testing for the classification module and restore these features to the original traffic for post event analysis and forensics. We used KDD cup 99 to train and test the model. Through this way, we could reduce the number of false alarms and increase the accuracy of the designed intrusion detection system.

Keywords: Intrusion detection system, Recurrent Neural Network, KDD cup99