Table 1.
Summary of recent related vision-based Android malware detection systems.
Fig 1.
The high-level description of the in-detail processes in the proposed comprehensive model.
Fig 2.
The flow of the proposed comprehensive model.
Fig 3.
Proposed scratch CNN algorithm.
Table 2.
Specifications of the CNN layers in the proposed scratch algorithm.
Table 3.
Simulation specifications of the examined CNN algorithms in the proposed comprehensive model.
Table 4.
Description of the examined android malware datasets.
Table 5.
Security performance of models on DREBIN dataset.
Table 6.
Security performance of models on AMD dataset.
Fig 4.
Confusion matrix of the proposed CNN algorithm (DAM format).
Fig 5.
DREBIN VS AMD in terms of best model acc-loss chart.
Table 7.
Comparative analysis: Percentage of the highest improved performance among different CNN models per metric and dataset type.
Table 8.
Complexity performance of models on DREBIN dataset.
Table 9.
Complexity performance of models on AMD dataset.
Fig 6.
DREBIN VS AMD in terms of speed of decompiling and unzipping processes.
Fig 7.
DREBIN VS AMD in terms of file size of APK images.
Fig 8.
DREBIN VS AMD in terms of file size of AM/DAM images.
Fig 9.
DREBIN VS AMD in terms of file size of CD/SMALI images.