N-Gram, Semantic-Based Neural Network for Mobile Malware Network Traffic Detection

Table 6

Description of detecting performance metrics of different flow composition architectures with different text sizes.

Flow composition type number	Evaluation metrics	Text size (byte) of the transformed data from network flow
		200	500	700	1000	1200	1500
1	Precision	0.847	0.894	0.954	0.969	0.971	0.971
	Recall	0.715	0.784	0.848	0.880	0.881	0.881
	F1-score	0.775	0.836	0.898	0.922	0.924	0.924
	Accuracy	0.772	0.836	0.899	0.924	0.925	0.926
2	Precision	0.846	0.894	0.955	0.969	0.971	0.971
	Recall	0.716	0.785	0.848	0.880	0.881	0.881
	F1-score	0.775	0.836	0.898	0.922	0.924	0.924
	Accuracy	0.772	0.836	0.899	0.924	0.925	0.926
3	Precision	0.848	0.895	0.954	0.970	0.971	0.971
	Recall	0.715	0.784	0.848	0.879	0.881	0.880
	F1-score	0.776	0.836	0.898	0.922	0.924	0.923
	Accuracy	0.772	0.836	0.899	0.924	0.925	0.925
4	Precision	0.846	0.894	0.956	0.970	0.971	0.971
	Recall	0.716	0.785	0.849	0.880	0.881	0.882
	F1-score	0.776	0.836	0.899	0.923	0.924	0.925
	Accuracy	0.772	0.837	0.899	0.925	0.926	0.926