IoT-CDS: Internet of Things Cyberattack Detecting System Based on Deep Learning Models

The rapid growth and pervasive presence of the Internet of Things (IoT) have led to an unparalleled increase in IoT devices, thereby intensifying worries over IoT security. Deep learning (DL)-based intrusion detection (ID) has emerged as a vital method for protecting IoT environments. To rectify the deficiencies of current detection methodologies, we proposed and developed an IoT cyberattacks detection system (IoT-CDS) based on DL models for detecting bot attacks in IoT networks. The DL models—long short-term memory (LSTM), gated recurrent units (GRUs), and convolutional neural network-LSTM (CNN-LSTM) were suggested to detect and classify IoT attacks. The BoT-IoT dataset was used to examine the proposed IoT-CDS system, and the dataset includes six attacks with normal packets. The experiments conducted on the BoT-IoT network dataset reveal that the LSTM model attained an impressive accuracy rate of 99.99%. Compared with other internal and external methods using the same dataset, it is observed that the LSTM model achieved higher accuracy rates. LSTMs are more efficient than GRUs and CNN-LSTMs in real-time performance and resource efficiency for cyberattack detection. This method, without feature selection, demonstrates advantages in training time and detection accuracy. Consequently, the proposed approach can be extended to improve the security of various IoT applications, representing a significant contribution to IoT security.