Threat detection in Internet of Things using Cuckoo search Chicken Swarm optimisation algorithm

Smart devices and people existing on the internet are connected to smart objects or things in the Internet of Things (IoT) technology. To protect the user information, it is required to detect malicious actions in the IoT environment. Even though different threat detection methods are introduced in the IoT technology, detecting malicious activity is still a significant challenge in the communication network. Hence, in this research work, an effective Cuckoo Search Chicken Swarm (CSCS) optimisation algorithm is proposed to detect the malicious threat in the network effectively. At first, the user activity information is simulated from the IoT network and stored in the user activity log. The user activity log file is forwarded to the feature extraction module, where the features, like logon, device, file, email, and Hypertext Transfer Protocol (HTTP) are extracted using the window length. For each user, the features are extracted with respect to the time stamp. Then, the dynamic feature index is constructed, and the threat detection is performed using the deep Long Short-Term Memory (LSTM) classifier, which is trained using the proposed CSCS algorithm. The proposed CSCS algorithm is designed by integrating the Cuckoo Search (CS) algorithm and the Chicken Swarm Optimisation (CSO) algorithm. Moreover, the proposed algorithm attained better performance with respect to the metrics, like namely F1-score, precision, and recall as 0.915, 0.975, and 0.884 by varying the k-value and 0.9286, 0.9235, and 0.9337 by varying the training data using window size as 10, respectively.