LAUSR

The Internet of Things (IoT) paradigm has matured and expanded rapidly across many disciplines. Despite these advancements, IoT networks continue to face an increasing security threat as a result of the constant and rapid changes in the network environment. In order to address these vulnerabilities, the Fog system is equipped with a robust environment that provides additional tools to beef up data security. However, numerous attacks are persistently evolving in IoT and fog environments as a result of the development of several breaches. To improve the efficiency of intrusion detection in the Internet of Things (IoT), this research introduced a novel tunicate swarm algorithm that combines a long-short-term memory-recurrent neural network. The presented model accomplishes this goal by first undergoing data pre-processing to transform the input data into a usable format. Additionally, attacks in the IoT ecosystem can be identified using a model built on long-short-term memory recurrent neural networks. There is a strong correlation between the number of parameters and the model’s capability and complexity in ANN models. It is critical to keep track of the number of parameters in each model layer to avoid over- or under-fitting. One way to prevent this from happening is to modify the number of layers in your data structure. The tunicate swarm algorithm is used to fine-tune the hyper-parameter values in the Long Short-Term Memory-Recurrent Neural Network model to improve how well it can find things. TSA was used to solve several problems that couldn’t be solved with traditional optimization methods. It also improved performance and shortened the time it took for the algorithm to converge. A series of tests were done on benchmark datasets. Compared to related models, the proposed TSA-LSTMRNN model achieved 92.67, 87.11, and 98.73 for accuracy, recall, and precision, respectively, which indicate the superiority of the proposed model.