Table 11.
Performance comparison with state-of-the-art methods using the same datasets.
| Work | Dataset | Strategy | Method | Accuracy (%) |
|---|---|---|---|---|
| Alani et al. [21] | CIC-AAGM2017 | Textual | MLP (DNN) | 98.02 |
| Acharya et al. [22] | CIC-AAGM2017 | Texture | CNN | 98.3 |
| Hadiprakoso et al. [23] | CICMalDroid 2020 | Textual | Gradient Boosting | 96.35 |
| Mohammad et al. [41] | CICMalDroid 2020 | Texture | CNN | 96.4 |
| Zhang et al. [24] | CICMalDroid 2020 | Texture | TCN | 95.44 |
| Mahdavifar et al. [25] | CICMalDroid 2020 | Textual | Ensemble | 97.84 |
| Peng et al. [42] | CICMalDroid 2020 | Texture | CNN | 98.6 |
| Our approach | CIC-AAGM2017 & CICMalDroid 2020 | Hybrid | Hybrid features with ensemble learning | 99 |