Resampling Imbalanced Network Intrusion Datasets to Identify Rare Attacks

This study, focusing on identifying rare attacks in imbalanced network intrusion datasets, explored the effect of using different ratios oversampled to undersampled data for binary classification. Two designs were compared: random undersampling before splitting training and testing after data. study also examines how oversampling/undersampling affect forest classification rates datasets with minority dataor attacks. The results suggest that gives better rates; however, oversampling BSMOTE allows use lower