EFS-DNN: An Ensemble Feature Selection-Based Deep Learning Approach to Network Intrusion Detection System

Table 6

Binary-class classification performance on NSL-KDD in terms of TPR (%), FPR (%), and Acc (%). EFS-DNN outperforms all baselines when the number of selected features is 15.

Method	TPR	FPR	Acc	# Features
TUIDS [41]	98.88	1.12	96.55	All
Hybrid IDS [42]	99.10	1.20	n/a	All
LSSVM-IDS + FMIFS [9]	98.93	0.28	99.40	18
DBN + ensemble SVM [18]	92.17	n/a	n/a	All
SwiftIDS [12]	99.59	0.20	99.60	All
PIO [10]	81.72	6.48	86.91	18
SMOTE-CFS [19]	70.00	6.00	81.00	13
SVM-IDS [24]	97.99	n/a	98.12	30
EFS-DNN	99.61	0.19	99.61	15