Table 5.
Summary of BotNet attack Detection using Deep Neural Network in an SDN-enabled IoT Networks.
Author | Method | Dataset | Acc (%) | P (%) | R (%) | F1 (%) |
---|---|---|---|---|---|---|
Khan et al. [93] | DNN-DNN | N_BaIoT | 99.93 | 99.87 | 99.86 | 99.86 |
Al-Abassi et al. [94] | DNN+DT | ICS | 99.67 | 97 | 99 | 99 |
Tang et al. [95] | DNN | NSL-KDD | 75.75 | 83 | 75 | 74 |
Narayanadoss et al. [96] | DNN | Simulated data | 85 | 87 | 87 | 87 |
Ferrag et al. [97] | DNN | CICDDoS2019 | 93.88 | 68 | 63 | 58 |
TON_IoT | 98.93 | 93 | 93 | 95 | ||
Ravi et al. [98] | DNN+K-means | NSL-KDD | 99.78 | - | - | 99.72 |
Makuvaza et al. [99] | DNN | CICIDS 2017 | 96.67 | 97.21 | 97.29 | 97.25 |
Ravi et al. [100] | Deep ELM | Simulated | 97.9 | 97.2 | 97.6 | 97.2 |
UNB-ISCX | 96.28 | 95.16 | 97.27 | 96.2 | ||
Maeda, Shogo et al. [101] | DNN | CTU-13 and ISOT | 98.7 | 98.99 | 99.70 | 99.34 |
Sattar et al. [102] | DNN-LSTM | N_BaIoT | 99.99 | 99.99 | 99.99 | 99.99 |