Table 5 Performance comparison of E-MGFlow with state-of-the-art method.

From: Research on encrypted malicious traffic detection in power information interaction: application of the electricity multi-granularity flow representation learning approach

Model

Precision (%)

Recall (%)

F1-score (%)

FPR (%)

Response time (ms)

Detection latency (ms)

E-MGFlow

93.64

93.76

93.55

6.52

90

140

Literature [26]

94.30

93.22

96.74

7.84

116

175

Back to article page