Leveraging sparrow search optimization with deep learning-based cybersecurity detection in industrial internet of things environment

The Industrial Internet of Things (IIoT) is a current research field that links digital services and equipment to physical methods. The IIoT was employed to make vast amounts of data from many sensors, and the device has met numerous issues. The IIoT has tackled several methods of cyberattacks that threaten its ability to distribute organizations with steady operations. Such threats result in reputational and financial spoils for businesses and the stealing of delicate data. Therefore, numerous network intrusion detection systems (IDSs) are proposed to address and defend against threats in IIoT environments. However, the data needed to develop an intelligent IDS is often complex and difficult to handle, resulting in significant challenges in detecting new and existing attack vectors. These complexities arise due to the dynamic nature of network traffic and growing cyberattack strategies, which require adaptive and advanced detection techniques. This study presents a Leveraging Sparrow Search Optimization Algorithm for a Deep Learning-Based Cybersecurity (LSSOA-DLBC) approach in the IIoTs environment. The LSSOA-DLBC approach aims to identify cybersecurity in the IIoT environment automatically. In the LSSOA-DLBC model, the first data normalization phase utilizes Z-score normalization. For the feature selection (FS) method, the LSSOA-DLBC model utilizes a sine cosine algorithm (SCA). Besides, the deep belief network (DBN) model automatically identifies cybersecurity in the IIoT environment. Eventually, the sparrow search algorithm (SSA) model is implemented to optimize the hyperparameter tuning of the DBN model. The experimental outcome of the LSSOA-DLBC methodology is examined on the benchmark dataset. The performance validation of the LSSOA-DLBC methodology portrays a superior accuracy value of 99.29 % over existing approaches concerning distinct evaluation metrics.