A Two-level Classification Method for Attacks on the Network

Abstract

With the development of computer network technology and the expanding application fields, the types of attacks on the system are becoming more and more complex. The systems security and attack classification are always two challenges for application service providers and enterprises. In recent years, many researchers have turned more attention to them and established evaluation and classifiers that can detect feature selection of network traffic anomalies. However, most research work does not cross-validate evaluation results, and there is no way to distinguish between different types of attacks. All kinds of facts prove that it is necessary to take appropriate countermeasures and defensive attacks. In this paper, we propose a classification framework and use a popular public data set KDD to establish a two-level similarity classification model. According to the attack similarity, our method can quickly and correctly classify the attacks. The experimental results show that our method is effective.