Table 1 Existing Android malware detection methods based on image-based deep learning algorithms.
From: Mobile malware detection method using improved GhostNetV2 with image enhancement technique
Reference | Model | Features | Image | Datasets | Accuracy (%) |
|---|---|---|---|---|---|
Ding et al. | CNN | classes.dex | grayscale | Drebin | 95.6 |
Singh et al. | Fusion-SVM | classes.dex | grayscale | Drebin | 93.24 |
Tang et al. | ResNet | classes.dex | grayscale | Drebin | 96.35 |
Zhang et al. | TCN | classes.dex,.xml | grayscale | Drebin | 95.44 |
Wang et al. | CNN | classes.dex,.xml | RGB | Drebin | 99.8 |
Yadav et al. | EfficientNetb4 | classes.dex | RGB | R2-D2 | 95.7 |
Ye et al. | CNN | classes.dex | RGB | CIC-AndMal-2017/2020 | 95.98 |
Ksibi et al | CNN | classes.dex | RGB | CICInvesAndMal2019 | 95.24 Â |
Zhu et al | EfficientNet | classes.dex | RGB | VirusShare | 96.9 |
Propsed | GhostNetV2 | classes.dex | RGB | CICAndMal2017/2020, VirusShare, Drebin | 97.7 |
