Stepping-Stone Intrusion Detection Using Neural Networks Approach

Abstract

-Attackers on the Internet typically launch network intrusions indirectly by creating a long connection via intermediary hosts, called stepping-stones. One way to detect such intrusion is to check the number of intermediary hosts. Neural networks provide the potential to identify and classify network activity. In this paper, we propose an approach to stepping-stone intrusion detection that utilizes the analytical strengths of neural networks. An improved scheme was developed for neural network investigation. This method clustered a sequence of consecutive Round-Trip Times (RTTs). It was found that neural networks were able to predict the number of stepping-stones for incoming packets by the proposed method without monitoring a connection chain all the time.