Table 9. Stacking classifier performance in Apache Tomcat (undersampled).

Approach	Classes	Accuracy	Precision	Recall	F1-Score
Stacking machine learning classifier (Ganesh, Palma & Olsson, 2022)	Vulnerable	77	41.5	87.2	56.24
	Severity	66.5	66.5	66.5	66.5
	Title	10.6	10.6	10.6	10.6
Our approach (stacking CNN classifiers)	Vulnerable	97.71	96.13	95.67	95.90
	Severity	94.72	79.96	71.92	73.95
	Title	93.14	52.30	52.22	49.08
Our approach (stacking CNN classifiers) (RUS)	Vulnerable	94.04	93.09	93.04	94.04
	Severity	73.05	72.62	73.05	72.52
	Title	74.24	60.13	59.91	57.30

Notes.

The bold values are the best results among other classifiers.