“…In general, the security issues faced by IoT devices are malware, weak password protection, exploitation, skill gaps, poor device management, insecure protocols, data leakage, firewall, secure booting, intrusion deception threat (IDT), authentication, and encryption [21][22][23]. Different methods have been utilized as defense strategies, such as (1) distributed deep learning (DDL) [24], (2) adversarial deep learning (ADL) [25], (3) the bidirectional short term memory based recurrent neural network (BLSTM-RNN) [26], (4) the artificial neural network (ANN) [27], (5) the deep neural network (DNN) [28], (6) existing network intrusion detection system (NIDS) implementation tools [29], (7) tensor DNN [30], (8) adversarial machine learning and other traditional methods (such as Petri Net) [25], (9) cloud-based distributed deep learning frameworks-(a) distributed convolution neural networks and (b) cloud based temporal long-short term memory [31]- (10) the uniform intrusion detection method [32], (11) the deep-learning-based intrusion detection system method with the combination of spider monkey optimization and a stacked-deep polynomial network [33], (12) the baptized BotIDS-based convolutional neural network [34], (13) CorrAUC [35], (14) K-nearest neighbors (KNN) and LSVM [36], (15) random forest (RF) [36][37][38], (16) neural networks [36,38], (17) decision trees (DTs) [36,37], and (18) supervised, unsupervised, semi-supervised, and reinforcement techniques [39,…”