Deep Encrypted Traffic Detection: An Anomaly Detection Framework for Encryption Traffic Based on Parallel Automatic Feature Extraction

<div>The left column indicates the three experimental evaluation metrics (accuracy, <i>F</i>1_score, and recall) of the unblocked serial automatic feature extraction algorithm, and the right column indicates the three experimental evaluation metrics of the parallel SAE feature extraction algorithm.</div>

Computational Intelligence and Neuroscience

fig4

Figure 4

Figure 4: Deep Encrypted Traffic Detection: An Anomaly Detection Framework for Encryption Traffic Based on Parallel Automatic Feature Extraction 