Malware Classification on Mal-Net
82.84AccuracyHuBERT ⊞ ViT (FOCA)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| HuBERT ⊞ ViT (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=HuBERT, Image Encoder=ViT, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 82.84 | 81.72 | |
| Wav2Vec2 ⊞ ViT (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=Wav2Vec2, Image Encoder=ViT, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 80.98 | 77.98 | |
| HuBERT ⊞ VGG-19 (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=HuBERT, Image Encoder=VGG-19, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 80.16 | 80.4 | |
| WavLM ⊞ ViT (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=WavLM, Image Encoder=ViT, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 79.73 | 80.1 | |
| Wav2Vec2 ⊞ ResNet-50 (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=Wav2Vec2, Image Encoder=ResNet-50, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 79.56 | 79.56 | |
| Wav2Vec2 ⊞ VGG-19 (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=Wav2Vec2, Image Encoder=VGG-19, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 79.27 | 78.7 | |
| HuBERT ⊞ ResNet-50 (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=HuBERT, Image Encoder=ResNet-50, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 79.27 | 80.2 | |
| WavLM ⊞ VGG-19 (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=WavLM, Image Encoder=VGG-19, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 78.84 | 78.18 | |
| WavLM ⊞ ResNet-50 (FOCA)Modality=Multi-modal (Audio ⊞ Image), Audio Encoder=WavLM, Image Encoder=ResNet-50, Fusion=Hyperbolic cross-attention (FOCA ⊞)2026.01 | 78.35 | 78.9 | |
| HuBERT ⊗ ViTModality=Multi-modal (Audio ⊗ Image), Audio Encoder=HuBERT, Image Encoder=ViT, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 76.78 | 74.77 | |
| Wav2Vec2 ⊗ ViTModality=Multi-modal (Audio ⊗ Image), Audio Encoder=Wav2Vec2, Image Encoder=ViT, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 74.86 | 72.89 | |
| Wav2Vec2 ⊗ ResNet-50Modality=Multi-modal (Audio ⊗ Image), Audio Encoder=Wav2Vec2, Image Encoder=ResNet-50, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 74.48 | 72.53 | |
| WavLM ⊗ ViTModality=Multi-modal (Audio ⊗ Image), Audio Encoder=WavLM, Image Encoder=ViT, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 74.11 | 72.22 | |
| HuBERT ⊗ VGG-19Modality=Multi-modal (Audio ⊗ Image), Audio Encoder=HuBERT, Image Encoder=VGG-19, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 74.01 | 72.13 | |
| HuBERT ⊗ ResNet-50Modality=Multi-modal (Audio ⊗ Image), Audio Encoder=HuBERT, Image Encoder=ResNet-50, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 73.71 | 71.78 | |
| Wav2Vec2 ⊗ VGG-19Modality=Multi-modal (Audio ⊗ Image), Audio Encoder=Wav2Vec2, Image Encoder=VGG-19, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 73.69 | 71.78 | |
| Wav2Vec2 + ResNet-50Modality=Multi-modal (Audio + Image), Audio Encoder=Wav2Vec2, Image Encoder=ResNet-50, Fusion=Concatenation (+)2026.01 | 73.4 | 69.7 | |
| WavLM ⊗ ResNet-50Modality=Multi-modal (Audio ⊗ Image), Audio Encoder=WavLM, Image Encoder=ResNet-50, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 73.29 | 71.35 | |
| WavLM ⊗ VGG-19Modality=Multi-modal (Audio ⊗ Image), Audio Encoder=WavLM, Image Encoder=VGG-19, Fusion=Euclidean cross-modal attention (⊗)2026.01 | 72.94 | 71.03 | |
| Wav2Vec2 + ViTModality=Multi-modal (Audio + Image), Audio Encoder=Wav2Vec2, Image Encoder=ViT, Fusion=Concatenation (+)2026.01 | 71.93 | 68.31 | |
| WavLM + ViTModality=Multi-modal (Audio + Image), Audio Encoder=WavLM, Image Encoder=ViT, Fusion=Concatenation (+)2026.01 | 71.2 | 67.61 | |
| Wav2Vec2 + VGG-19Modality=Multi-modal (Audio + Image), Audio Encoder=Wav2Vec2, Image Encoder=VGG-19, Fusion=Concatenation (+)2026.01 | 70.98 | 67.43 | |
| HuBERT + ViTModality=Multi-modal (Audio + Image), Audio Encoder=HuBERT, Image Encoder=ViT, Fusion=Concatenation (+)2026.01 | 70.66 | 67.03 | |
| WavLM + ResNet-50Modality=Multi-modal (Audio + Image), Audio Encoder=WavLM, Image Encoder=ResNet-50, Fusion=Concatenation (+)2026.01 | 70.46 | 66.91 | |
| HuBERT + ResNet-50Modality=Multi-modal (Audio + Image), Audio Encoder=HuBERT, Image Encoder=ResNet-50, Fusion=Concatenation (+)2026.01 | 70.19 | 66.53 | |
| Scott et al.2026.01 | 70.12 | 67.71 | |
| HuBERT + VGG-19Modality=Multi-modal (Audio + Image), Audio Encoder=HuBERT, Image Encoder=VGG-19, Fusion=Concatenation (+)2026.01 | 70.03 | 66.41 | |
| WavLM + VGG-19Modality=Multi-modal (Audio + Image), Audio Encoder=WavLM, Image Encoder=VGG-19, Fusion=Concatenation (+)2026.01 | 69.73 | 66.22 | |
| Wav2Vec2Modality=Audio, Audio Encoder=Wav2Vec22026.01 | 68.82 | 65.46 | |
| HuBERTModality=Audio, Audio Encoder=HuBERT2026.01 | 64.69 | 61.53 | |
| WavLMModality=Audio, Audio Encoder=WavLM2026.01 | 63.31 | 60.22 | |
| ViTModality=Image, Image Encoder=ViT2026.01 | 62.9 | 58.48 | |
| VGG-19Modality=Image, Image Encoder=VGG-192026.01 | 61.01 | 56.73 | |
| ResNet-50Modality=Image, Image Encoder=ResNet-502026.01 | 59.87 | 55.61 | |
| Yang et al.2026.01 | 53.71 | 53.65 | |
| Devnath et al.2026.01 | 52.49 | 51.21 | |
| Vasan et al.2026.01 | 48.54 | 51.67 | |
| Samaneh et al.2026.01 | 41.73 | 40.84 |