Cybersecurity

Table 4 Performance metrics (weighted) of the model utilizing diverse ensemble techniques

From: Enhanced detection of obfuscated malware in memory dumps: a machine learning approach for advanced cybersecurity

Metrics	Without balancing					Balancing with SMOTE
Metrics	GB	RF	BG	VT	ADB	GB	RF	BG	VT	ADB
ACC	0.99966	0.99932	0.99932	0.99951	0.83378	1.0000	0.99956	0.99997	0.99997	0.74783
PR	0.99966	0.99932	0.99932	0.99951	0.91541	1.0000	0.99956	0.99997	0.99997	0.87412
RE	0.99966	0.99932	0.99932	0.99951	0.83378	1.0000	0.99956	0.99997	0.99997	0.74783
FS	0.99966	0.99932	0.99932	0.99951	0.77772	1.0000	0.99956	0.99997	0.99997	0.66387
FPR	0.00017	0.00021	0.00021	0.00011	0.05020	1.0000	0.00015	0.00001	0.00001	0.08421
ER	0.00034	0.00068	0.00068	0.00049	0.16622	1.0000	0.00044	0.00003	0.00003	0.25217
CK	0.99949	0.99898	0.99898	0.99937	0.75105	1.0000	0.99941	0.99995	0.99995	0.66386
AUC	1.00000	0.99998	1.00000	0.99999	0.91667	1.0000	0.99997	1.00000	1.00000	0.91667

Back to article page