Research Article
[Retracted] Software Defined Network Enabled Fog-to-Things Hybrid Deep Learning Driven Cyber Threat Detection System
Table 1
Comprehensive comparison of existing related work.
| Ref | Year | Dataset | Algorithms | Findings |
| [7] | 2018 | ISCX, AWID | LSTM, LR | 98.22% accuracy achieved in multiclass | [8] | 2019 | MAWI | RNN, CNN | 98% accuracy achieved in multiclass | [9] | 2020 | NSL-KDD | ML and DL | 99% accuracy achieved in multiclass | [10] | 2020 | NSL-KDD | Multilayered RNN | 92.18% accuracy achieved in multiclass | [11] | 2021 | IoTID20 | Exact greedy algorithm | 84.4% accuracy achieved in multiclass | [12] | 2018 | 5G data | CCA security model | Proposed model provides security using encryption method | [13] | 2017 | Coca-Cola dataset | AES algorithm | Data is secured through encryption | [14] | 2016 | CIDDS-01 | NIDS | Data is protected through NIDS | [15] | 2021 | SDN port data | IoT-DDoS algorithm | DDoS SDN-enabled model successfully detects and prevents attacks | [16] | 2021 | Survey paper | IDS algorithms | Fog models detect attacks with low accuracy rate | [17] | 2021 | SOHO architecture data | DL algorithms | 99.66% anomaly detection network accuracy rate in IEEE 802.11 |
|
|