Table 8 Statistical significance analysis comparing the proposed CNN-Attention + Fine-Tuned decision tree model with baseline classifiers across CIC-IDS2017 and NSL-KDD datasets.
Compared Model | Dataset | Accuracy Gain (%) | p-value (Accuracy) | F1 Gain (%) | p-value (F1) | Statistically Significant? |
|---|---|---|---|---|---|---|
CNN + XGBoost | CIC | 0.9 | 0.075 | 0.8 | 0.092 | No |
CNN + Softmax | CIC | 3.5 | 0.013 | 3.4 | 0.019 | Yes |
CNN + DT | CIC | 5.1 | 0.002 | 5 | 0.003 | Yes |
CNN + XGBoost | NSL | 1.1 | 0.081 | 1 | 0.088 | No |
CNN + Softmax | NSL | 4.2 | 0.017 | 4.1 | 0.021 | Yes |
CNN + DT | NSL | 5.7 | 0.001 | 5.6 | 0.001 | Yes |
