i-2NIDS Novel Intelligent Intrusion Detection Approach for a Strong Network Security

The potential of machine learning mechanisms played a key role in improving the intrusion detection task. However, other factors such as quality data, overfitting, imbalanced problems, etc. may greatly affect performance an intelligent system (IDS). To tackle these issues, this paper proposes novel learning-based IDS called i-2NIDS. novelty approach lies application nested cross-validation method, which necessitates using two loops: outer loop is for hyper-parameter selection that costs least error during run small amount training set and inner estimation test set. experiments showed significant improvements within NSL-KDD dataset with accuracy rate 99.97%, 99.79%, 99.72%, 99.96%, 99.98% detecting normal activities, DDoS/DoS, Probing, R2L U2R attacks, respectively. obtained results approve efficiency superiority over recent existing experiments.