Defending Malicious Script Attacks Using Machine Learning Classifiers

Table 2

Results obtained from four classifiers by using 100% training.

Classifier	Accuracy	TP rate	FP rate	Precision	Recall	-measure	ROC	Class
Naïve Bayes	97.25%	0.875	0.001	0.994	0.875	0.931	0.943	Malicious
		0.999	0.125	0.967	0.999	0.983	0.943	Nonmalicious
J48	97.09%	0.966	0.003	0.99	0.966	0.978	0.982	Malicious
		0.997	0.034	0.991	0.997	0.994	0.982	Nonmalicious
SVM	96.51%	0.912	0.02	0.923	0.912	0.918	0.946	Malicious
		0.98	0.088	0.976	0.98	0.978	0.946	Nonmalicious
KNN	100.00%	1	0	1	1	1	1	Malicious
		1	0	1	1	1	1	Nonmalicious