Attack Classification of Imbalanced Intrusion Data for IoT Network Using Ensemble-Learning-Based Deep Neural Network

With the increase in popularity of Internet of Things (IoT) and the rise in interconnected devices, the need to foster effective security mechanism to handle vulnerabilities and risks in IoT networks has become evident. Security mechanisms, such as intrusion detection system (IDS), are designed and deployed in IoT network environment to ensure security and prevent unauthorized access to system and resources. Moreover, there have been efforts to design IDS using various deep learning (DL) techniques, as these techniques possess the intriguing characteristic of representing data with high abstraction. However, the intrusion detection data sets used in literature possess imbalance class distribution, which is one of the challenging issues in developing coherent and potent intrusion detection and classification system. In this article, we aim to address class imbalance problem using ensemble learning approach, namely, the Bagging classifier, that uses a deep neural network (DNN) as a base estimator. Here, in the proposed approach, the training process of DNN is influenced by, including class weights that advocates to create balanced training subsets for DNN. The desirability and merit of the proposed approach can be considered as twofold as it aims to achieve generalization along with addressing the class imbalance problem in intrusion detection data sets. The performance of the proposed approach is evaluated using four intrusion detection data sets, namely, NSL-KDD, UNSW_NB-15, CIC-IDS-2017, and BoT-IoT. The result analysis of the proposed approach is illustrated using various evaluation metrics, namely, accuracy, precision, recall,
$f$
-score, and false positive rate (FPR). Moreover, the results of the proposed approach are also statistically tested using Wilcoxon signed-rank test.