Frequency-Based Representation of Massive Alerts and Combination of Indicators by Heterogeneous Intrusion Detection Systems for Anomaly Detection

Although the application of a wide range of sensors has been generalized through the development of technology, the processing of massive alerts generated through data analysis and monitoring remains a challenge. This problem is also found in cyber security because the intrusion detection system (IDS) produces a tremendous number of alerts. Massive alerts not only significantly increase resources for analysis, but also make it difficult to analyze the overall situation of the system. In order to handle massive alerts, we propose using an indicator as a frequency-based representation. The proposed indicator is generated from categorical parameters of alerts that occur within a unit time utilizing frequency and is used for situational awareness with machine learning to detect whether there is a threat or not. The advantage of using indicators is that they can determine the situation for a period without analyzing individual alerts, which helps security experts to recognize the situation in the system and focus on targets that require in-depth analysis. In addition, the conversion from the categorical parameters which is highly related to analysis to numeric parameter allows for applying machine learning. For performance evaluation, we collect data from an HAI testbed similar to real critical infrastructure and conduct experiments using indicators and XGBoost, a classification machine learning algorithm against five famous vulnerability attacks. Consequently, we show that the proposed method can detect attacks with more than 90 percent accuracy, and the performance is enhanced using heterogeneous intrusion detection systems.