Abstract
A machine-based intrusion sensing system has become an essential component in network safeguarding and information security due to the regular development of large volumes of data and the increasing interconnection among global Internet infrastructures. Previous shallow learning and deep learning techniques follow a similar model learning approach to intrusion detection. To explain the increasingly complex data delivery intrusion patterns, a single learning model methodology can face problems. Specifically, a single deep learning model cannot capture special patterns in intrusive attacks with a few experiments. We propose a hierarchical deep learning system based on big data to further boost the efficiency of IDS-based machine learning. It uses behavioral and content-functional functionality to capture both network traffic and content details. Each deep learning model in the proposed framework focuses on learning the particular data distribution in a single cluster. Compared to previous single learning models, this technique improves the classification rate of disruptive attacks. The model building time of the system is reduced considerably when several devices are implemented.