Table 8 Results of ablation experiments(Microsoft Malware Classification Challenge).
From: GCSA-ResNet: a deep neural network architecture for Malware detection
Model | accuracy | precision | Recall-mic | Recall-mac | F1 -mic | F1-mac | F1-wei | SPC | FPR | NPV | DE | Time |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
CA-resnet | 97.99 | 97.99 | 97.99 | 97.61 | 97.99 | 97.66 | 97.99 | 99.71 | 0.27 | 99.72 | 99.56 | 2191 |
SA-Resnet | 97.85 | 97.85 | 97.85 | 97.55 | 97.85 | 97.62 | 97.86 | 99.73 | 0.27 | 99.75 | 99.56 | 2255 |
CSA-Resnet | 98.08 | 98.08 | 98.08 | 97.94 | 98.08 | 97.93 | 98.08 | 99.74 | 0.26 | 99.74 | 99.54 | 2282 |
GCSA-Resnet | 98.58 | 98.58 | 98.58 | 98.35 | 98.58 | 98.37 | 98.58 | 99.82 | 0.18 | 99.82 | 99.69 | 2324 |
