An Improved Convolutional Neural Network Model for Intrusion Detection in Networks

Network intrusion detection is an important component of network security. Currently, the popular detection technology used the traditional machine learning algorithms to train the intrusion samples, so as to obtain the intrusion detection model. However, these algorithms have the disadvantage of low detection rate. Deep learning is more advanced technology that automatically extracts features from samples. In view of the fact that the accuracy of intrusion detection is not high in traditional machine learning technology, this paper proposes a network intrusion detection model based on convolutional neural network algorithm. The model can automatically extract the effective features of intrusion samples, so that the intrusion samples can be accurately classified. Experimental results on KDD99 datasets show that the proposed model can greatly improve the accuracy of intrusion detection.

I. Introduction

With the development of Internet technology, more and more physical devices are connected to the Internet. The connection between devices resulted in a large amount of data being generated and saved. The era of “big data” came into being, however, some valuable data is exposed due to lack of protection measures especially when the device transmits data through continuous connection, thus causing huge losses to individuals and even to the whole country [1]. Many machine learning algorithms are used for malware/intrusion detection so far. Khan et. al. [2], [3] analysed ResNet and GoogleNet models for malware detection which are based on CNN. Kumar et. al. [4] used CNN model for malicious code detection based on pattern recognition. With the increasing number of networked devices, network systems will become more vulnerable. This gives hackers an opportunity to steal data, user privacy, and trade secrets more easily [5]. Although people have tried their best to protect their important information, due to the complexity of the network system and the richness of attack methods, cyber attacks continue to occur [6]. Given these circumstances, cyber attack detection methods should be smarter and more efficient than ever before, in order to detect and prevent the growing hacking technology. This paper presents a method of network anomaly detection based on deep learning. Experimental results show that this method can identify daily cyber attacks quickly and efficiently.