Journal of Big Data

Table 25 Mean performance of 7 classifiers in terms of AUC and F1-score on datasets with features from feature group 1A

From: Detecting cybersecurity attacks across different network features and learners

Classifier	Feature group 1A
Classifier	AUC	SD AUC	F1	SD F1
CatBoost	0.94200	0.00870	0.91650	0.01075
LightGBM	0.96147	0.00087	0.94690	0.00062
Decision Tree	0.90891	0.00022	0.88583	0.00031
Logistic Regression	0.66772	0.00134	0.49471	0.00288
Naive Bayes	0.56711	0.00023	0.24319	0.00061
Random Forest	0.95132	0.00782	0.92949	0.00845
XGBoost	0.95385	0.00020	0.93647	0.00032

Best metrics are highlighted in italics; SD AUC is the standard deviation of AUC and SD F1 is the standard deviation of the F1-score

Back to article page