Skip to main content

Advances, Systems and Applications

Table 1 NSL-KDD data distribution

From: Research on unsupervised anomaly data detection method based on improved automatic encoder and Gaussian mixture model

Data Category

Training set (percentage)

Test set (percentage)

Normal

67,343 (53%)

9711 (43%)

DoS

45,927 (37%)

7458 (33%)

Probe

11,656 (9.11%)

2421 (11%)

R2L

995 (0.85%)

2654 (12.1%)

U2R

52 (0.04%)

200 (0.9%)

Total

125,973

22,544