Advances, Systems and Applications
Table 1 Comparison of various existing methods in the field of IoT cyber threats
Ref | Technique | Dataset | Model Type | Evaluation parameter | Limitations |
|---|---|---|---|---|---|
[12] | Contextual information, Light probe model | Synthetic data | Binary classification | Accuracy 86.15% | inefficient in the reading of the sensor |
[13] | Binary visualization, Convolutional Neural Network Model | KDD dataset | Multi-class | Accuracy 92.82% | Not capable of predicting all types of attacks |
[1] | Random forest model, Logistic Regression | DS20S-traffic | Binary classification | Accuracy 94.31% | Requires high computational facilities |
[14] | Naïve Bayes with Long Short-Term Memory (LSTM) | NSL dataset | Multi-class | Accuracy 94.31% | Not dynamics |
[15] | Logistic Regression | IDS dataset | Binary classification | Accuracy 90.27 | Failed in real-time scenarios |
[16] | Neural Network Model | Synthetic data | Multi-class | Accuracy 91.47 | Slow in big-size dataset |
[17] | Regression Model with SVM model | Synthetic data | Binary classification | Accuracy 90.47 | Speed slow |
[18] | K-nearest neighbour with Xgboost | Online IoT dataset | Multi-class | Accuracy 89.97 | Limited Training Data |
[19] | AdaBoost and Decision Tree | Synthetic data | Binary classification | Accuracy 93.77 | Data Imbalance |
[20] | Gradient boosted machine and ANN model | Online IoT dataset | Binary classification | Accuracy 90.07 | less effective if not updated regularly |
Proposed Model | Optimized CHAID Decision Tree and Multi Class SVM fusion | Online IoT attack dataset | Multi-class | Accuracy 99.97 |