Intrusion Detection Systems Based on Logarithmic Autoencoder and XGBoost

Table 4

Ablation experiment: comparison between LogAE-XGBoost and XGBoost

Data set	Classifier	Accuracy	Precision	Recall	F1-score
UNSW-NB15	LogAE-XGBoost	0.9511	0.9549	0.9743	0.9645
	XGBoost	0.9023	0.9874	0.8676	0.9236
CICIDS2017	LogAE-XGBoost	0.9992	0.9971	0.9986	0.9979
	XGBoost	0.9943	0.9922	0.9930	0.9925