Robust Anomaly Detection based on Ensemble Model through Efficient Extraction of Normal Traffic Information

点击翻译按钮获取中文摘要

I proposed an anomaly detection method that trains a baseline model describing the normal behavior of network traffic using normal traffic information which is efficiently extracted through time-periodical packet sampling. In addition, in order to improve detection performance and adjust alarm sensitivity, I proposed an ensemble anomaly detection that collectively exploits multiple baseline models in parallel. Theoretical analysis and testing using actual traffic traces showed that the proposed anomaly detection methods perform well.