Research Article
[Retracted] Software Defined Network Enabled Fog-to-Things Hybrid Deep Learning Driven Cyber Threat Detection System
Table 7
Proposed framework comparison with existing state-of-the-art solutions for cyber threats detection.
| Frameworks | Algorithm | Dataset | Accuracy (%) | Precision (%) | Recall (%) | F1-score (%) | Time |
| Proposed | LSTM-CNN | CIDDS2017 | 99.92 | 99.85 | 99.85 | 99.91 | 29 | [7] | LSTM | AWID | 98.22 | 98.9 | 98.5 | 98.38 | — | [8] | RNN, CNN | MAWI | 99.56 | 99.11 | 99.01 | 99.21 | — | [9] | CNN-LSTM | CIDDS2017 | 98.88 | 98.41 | 99.8 | 99.1 | 549 | [10] | RNN | NSL-KDD | 92.18 | 90.23 | 90.8 | 92.29 | — | [11] | MLP | IoTID2020 | 84.4 | 78 | 91 | 84 | — | | XGBoost | — | 98 | 91 | 63 | 75 | — |
|
|