Table 1.
Related studies on IDS using deep learning.
Fig 1.
A diagram showing the workflow of the proposed architecture with hyperparameters to classify intrusions.
Fig 2.
A diagram showing the workflow of the proposed novel hybrid- MCL-FWA-BILSTM based architecture to classify intrusions.
Table 2.
Description of the NSL-KDD dataset attack categories.
Table 3.
Attack types and their description in the UNSW-NB15 dataset.
Fig 3.
The architecture of the BI-LSTM model.
Fig 4.
Confusion matrix related to IDS for performance evaluation.
Table 4.
Confusion matrix of NSL-KDD on the proposed approach.
Table 5.
Performance metrics of NSL-KDD dataset using MCL-FWA-BILSTM model.
Fig 5.
MCL-FWA-BILSTM model precision, DR, F-Score and FPR comparison on NSL-KDD dataset.
Fig 6.
Binary classification accuracy and DR comparison on NSL-KDD.
Table 6.
Confusion matrix of UNSW-NB-15 dataset using MCL-FWA-BILSTM approach.
Table 7.
Performance Metrics of the UNSW-NB15 dataset on the proposed approach.
Fig 7.
MCL-FWA-BILSTM model precision, DR, F-Score and FPR comparison on UNSW-NB15.
Fig 8.
Comparison of accuracy and DR on UNSW-NB15.
Fig 9.
MCL-FWA-BILSTM binary and multiclass accuracy comparison.
Fig 10.
Comparison of accuracy of MCL-FWA-BILSTM model with existing models for binary classification on UNSW-NB15 and NSL-KDD.
Fig 11.
MCL-FWA-BILSTM accuracy comparison with existing approaches for multiclass classification.
Fig 12.
Comparison of DR and FPR of UNSW-NB15.
Fig 13.
F-Score, DR and FPR comparison for multiclass classification on UNSW-NB15.
Fig 14.
Minority attack class detection rate of UNSW-NB15 using MCL-FWA-BILSTM model.
Fig 15.
Comparison of DR and FPR of NSL- KDD dataset using MCL-FWA-BILSTM model.
Fig 16.
F-score, DR and FPR comparison for multiclass on NSL-KDD using MCL-FWA-BILSTM.
Fig 17.
Minority attack class detection rate of NSL-KDD dataset using MCL-FWA-BILSTM model.
Fig 18.
Accuracy measures for MCL, FWA-BILSTM and proposed MCL-FWA-BILSTM.
Table 8.
Accuracy comparison with existing approaches for Binary Classification with state of art on UNSW-NB15 and NSL-KDD.
Table 9.
Accuracy comparison with existing approaches for binary classification with state of art on UNSW-NB15 and NSL-KDD.
Table 10.
MCL-FWA-BILSTM accuracy comparison with existing approaches for multiclass classification with state of art on UNSW-NB15 and NSL-KDD.
Table 11.
MCL-FWA-BILSTM accuracy comparison with existing approaches for multiclass classification with state of art on UNSW-NB15 or NSL-KDD.
Table 12.
a. MCL-FWA-BILSTM comparison with the state of art on UNSW-NB15.
b. MCL-FWA-BILSTM model DR and FPR achievement.
Table 13.
MCL-FWA-BILSTM comparison with the state of art on NSl-KDD.
Table 14.
MCL-FWA-BILSTM and other existing approaches for multiclass classification in both datasets.