Host Behavior in Computer Network: One-Year Study

An analysis of a host behavior is an essential key for modern network management and security. A robust profile enables the managers to detect anomalies with high accuracy, predict behavior, or group clusters better management. Hence, profiling methods attract interest many researchers, novel are being introduced. However, these frequently developed on preprocessed small datasets. Therefore, they do not reflect real-world artifacts profiling, such as missing observations, temporal patterns, variability in characteristics time. To provide needed insight into settings, we present study conducted one-year-long dataset. In study, inspect availability data identify patterns introduce method stable labeling hosts, assess course year using coefficient variance. Moreover, make one-year dataset containing nine used available public use further research, including selected cases representing caveats. We also share record presented paper.