Network behavior anomaly detection (NBAD) is the continuous monitoring of a network for unusual events or trends. Ideally, an NBAD program tracks critical network characteristics in real time and generates an alarm if a strange event or trend is detected that indicates a threat. In this recipe, we will build an NBAD using machine learning.
The dataset used is a modified subset from a famous dataset known as the KDD dataset, and is a standard set for testing and constructing IDS systems. This dataset contains a wide variety of intrusions simulated in a military network environment.
