A Fast Probing Detection Method using Hybrid Machine Learning Algorithms

Abstract

Recently, a malicious user breaks into the network and destroys the entire network. This attack starts from probing. In this paper, we propose a fast probing detection technique for intrusion detection. In the past, probing detection was performed by analyzing all collected traffic characteristics and by supervised learning. In the proposed method, a normal traffic is classified through unsupervised learning and intrusion detection for probing attack is not performed for that traffic. The supervised learning is performed on traffic that may be abnormal. So, through the simulation, we verify that the proposed method can reduce times than the conventional method.