Improving the Accuracy of Network Intrusion Detection with Causal Machine Learning

Table 16

Comparison of accuracy between CFS and CRFS in the NSL-KDD dataset.

Feature selection method	Accuracy under different types of cyberattacks (1, 7)
	1	7
KNN-CFS	0.9835	0.9681
KNN-CFS (do)	0.9835	0.9624
Percentage	1	0.9960