A CNN-LSTM Model for Intrusion Detection System from High Dimensional Data
K. Prasanna
Abstract
Network protection is an essential part of attack detection. Machine learning<br> algorithms play an important role in the current Intrusion Detection. However, these<br> algorithms are suffering with low accuracy and detection rate. Deep learning is another<br> sophisticated technique to solve these challenges because intrusion detection<br> performance is not strong in traditional machine learning systems. This article examines<br> network intrusion detection using a Convolutional Neural Network (CNN) and LSTM.<br> The integrated folding and grouping operations are used to derive the relationship of the<br> features between the results. The model should automatically determine the efficient<br> properties of the intrusion samples so that the intrusion samples can be classified<br> accurately. Experimental tests with KDD99 data sets suggest that the proposed model<br> will significantly increase intrusion detection performance.