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

<div>Binary-class classification performance of EFS-DNN in terms of accuracy on three benchmark datasets under different feature selection thresholds and different sample ratios. (a) KDD 99. (b) NSL-KDD. (c) UNSW-NB15.</div>

Security and Communication Networks

fig3

Figure 3

Figure 3: EFS-DNN: An Ensemble Feature Selection-Based Deep Learning Approach to Network Intrusion Detection System 