Table 9 Comparing our model’s AUC and F1-Score with other studies in the literature in the CSE-CIC-IDS2018 dataset
Reference | Method | FS Method | AUC | F1-Score |
|---|---|---|---|---|
Leevy [53] | CatBoost | / | 0.956 | 0.936 |
Decision Tree | / | 0.911 | 0.887 | |
LightGBM | / | 0.951 | 0.929 | |
Naive Bayes | / | 0.553 | 0.314 | |
Random Forest | / | 0.955 | 0.932 | |
XGBoost | / | 0.913 | 0.889 | |
DKNN [54] | Kronecker neural network | CRDO | / | 0.960 |
MP-CVAE [55] | Variational Autoencoder | / | 0.94 | 0.95 |
ICVAE-BSM [56] | Variational Autoencoder | BPSO | 0.964 | 0.955 |
ID-RDRL [22] | Deep Q-Learning | RFE | 0.983 | 0.948 |
Our model | Deep Q-Learning | MAFS | 0.990 | 0.963 |