Table 4.

Performance of machine learning and deep learning models for threat Detection.

Model	Type & Category	Accuracy	Precision	Recall	F1-Score	Detection Rate	FPR	Execution Time (s)
Naive Bayes	Probabilistic, ML	0.892	0.885	0.890	0.887	0.9941	0.908	0.084
SVM	Kernel-based, ML	0.665	0.952	0.665	0.757	0.964	0.351	1.457
LSTM	Recurrent Neural Net, DL	0.900	0.964	0.900	0.921	0.976	0.091	38.075
BERT	Transformer-based, DL	0.950	0.971	0.950	0.957	0.950	0.050	382.144