Table 7 Comparison of ET-SSL with baseline models.
From: Anomaly detection in encrypted network traffic using self-supervised learning
Model | Accuracy (%) | Precision (%) | Recall (%) | F1-score (%) |
|---|---|---|---|---|
Supervised (Random Forest) | 88.3 | 85.7 | 84.5 | 85.1 |
Unsupervised (K-Means) | 82.9 | 80.4 | 79.1 | 79.7 |
Deep Autoencoder | 90.5 | 88.3 | 87.2 | 87.7 |
ET-SSL (proposed model) | 96.8 | 95.5 | 94.3 | 94.9 |
