FGL_Droid: An Efficient Android Malware Detection Method Based on Hybrid Analysis

Table 1

Comparison of the proposed work with state-of-the-art android malware detection schemas.

Schema	Features	Classification algorithm	Computational overheads	Capacity of saving information
[1]	Statistical features of API call sequence	SVM	Medium	Low
[2]		DNN
[3]		XGBoost
[7]	A fixed-length subsequence of API call sequence	LSTM	High	Medium
[10]		CNN + LSTM
[11]		RNN
Ours	Function call graph + permission	GCN + LR	Low	High