Advances, Systems and Applications
Table 8 Summary of selected works on using ML/DL for cyber security without CEP technology
Paper | Year | Threat | Techniques | Dataset |
|---|---|---|---|---|
[102] Meidan et al. | 2017 | Unauthorized IoT | Random forests | Simulation |
[105] Yuan et al. | 2017 | DDoS attack | CNN, RNN models such as LTSM or GRU. | ISCX2012 |
[104] Meidan et al. | 2018 | Abnormalities network traffic from IoT devices | Deep autoencoder (AE) | N-BaIoT |
[105] Ibitoye et al. | 2019 | DDoS attack | Self-normalizing Neural Network (SNN) | BoT-IoT UNSW |
[101] Anthi et al. | 2019 | Reconnaissance, DoS/DDoS, and spoofing | Naive-Bayes, SVM, decision tree, and random forest. | Simulation |
[107] Thamilarasu et al. | 2019 | DDoS attack, opportunistic service attack, blackhole, wormhole and sinkhole attacks. | Deep belief network (DBN), | Own testbed |
[100] Jithu et al. | 2021 | DDoS attack | Deep neural network (DNN) | BoT-IoT UNSW |