Research on intrusion detection technology based on deep learning

Abstract

With the popularity of digital technology in various fields, increasingly importance has been attached to security of computer networks over the last decade. There is a great need of highly accurate intrusion detection system which are design to prevent attacks. Deep learning has been proved to be the most efficient method to detect intrusion. In this paper, we proposed a deep neural network (DNN) model to identify anomalies in network data. The model is mainly composed of multi-layer fully connected layer and dropout layer. Adam algorithm is used in the model to prevent the detection model from falling into local minimum and speed up training speed. ReLU (Rectified linear unit) is used as the activation function of each layer, and Softmax is used as the output layer activation function to finalize the classification. Finally, the DNN model is investigated and tested with the KDD CUP 99 dataset. Simulation results show that the performance of the model is better than the other models.