Network Attack Traffic Detection for Calculating Correlation of the Flow

As the propagation of high-speed Internet and the rapid development of the network environment have led to an increase of various types of attack traffic. To cope with the various types of attack traffic, it is essential to detect these traffic accurately. There are many ways to detect traffic, and the most common methods are signature-based analysis and machine learning-based analysis. Both methods have the advantage of being able to detect with high accuracy, but both methods have several limitations in processing. In this paper, we propose a classification method with sequential grouping based on correlation of the flow. The proposed method is a method of calculating the correlation of two flows with the attack flow information, and then detecting the related attack flow based on that. As a result of applying the proposed method to real attack traffic, we could detect with high accuracy.