Internet of Things (IoT) networks present unique cybersecurity challenges due to their distributed and heterogeneous nature. Our study explores the effectiveness of two types of deep learning models, long-term memory ...Internet of Things (IoT) networks present unique cybersecurity challenges due to their distributed and heterogeneous nature. Our study explores the effectiveness of two types of deep learning models, long-term memory neural networks (LSTMs) and deep neural networks (DNNs), for detecting attacks in IoT networks. We evaluated the performance of six hybrid models combining LSTM or DNN feature extractors with classifiers such as Random Forest, k-Nearest Neighbors and XGBoost. The LSTM-RF and LSTM-XGBoost models showed lower accuracy variability in the face of different types of attack, indicating greater robustness. The LSTM-RF and LSTM-XGBoost models show variability in results, with accuracies between 58% and 99% for attack types, while LSTM-KNN has higher but more variable accuracies, between 72% and 99%. The DNN-RF and DNN-XGBoost models show lower variability in their results, with accuracies between 59% and 99%, while DNN-KNN has higher but more variable accuracies, between 71% and 99%. LSTM-based models are proving to be more effective for detecting attacks in IoT networks, particularly for sophisticated attacks. However, the final choice of model depends on the constraints of the application, taking into account a trade-off between accuracy and complexity.展开更多
文摘Internet of Things (IoT) networks present unique cybersecurity challenges due to their distributed and heterogeneous nature. Our study explores the effectiveness of two types of deep learning models, long-term memory neural networks (LSTMs) and deep neural networks (DNNs), for detecting attacks in IoT networks. We evaluated the performance of six hybrid models combining LSTM or DNN feature extractors with classifiers such as Random Forest, k-Nearest Neighbors and XGBoost. The LSTM-RF and LSTM-XGBoost models showed lower accuracy variability in the face of different types of attack, indicating greater robustness. The LSTM-RF and LSTM-XGBoost models show variability in results, with accuracies between 58% and 99% for attack types, while LSTM-KNN has higher but more variable accuracies, between 72% and 99%. The DNN-RF and DNN-XGBoost models show lower variability in their results, with accuracies between 59% and 99%, while DNN-KNN has higher but more variable accuracies, between 71% and 99%. LSTM-based models are proving to be more effective for detecting attacks in IoT networks, particularly for sophisticated attacks. However, the final choice of model depends on the constraints of the application, taking into account a trade-off between accuracy and complexity.
