Leveraging hybrid deep learning with starfish optimization algorithm based secure mechanism for intelligent edge computing in smart cities environment

The Internet of Things (IoT) now appears in each domain, from smart cities to home applications. The widespread use of IoT is making its security a real concern. The past few years have revealed an extraordinary increase in computer-intensive applications. Such applications always make huge volumes of data that demand severe latency-aware computational processing abilities. While edge computing is one of the attractive technologies for balancing severe latency-related problems, its deployment produces novel tasks. Edge computing is an innovative model distinguished mainly by its mobility support, geo-distributed process, low latency, and context awareness. However, recent edge computing developments have begun to explore novel IoT potentials that are leveraged from a security perspective. Methods depend upon artificial intelligence (AI) and its subgroups, machine learning (ML) and deep learning (DL), are generally employed to develop a safe Intrusion Detection System (IDS) for IoT. This study proposes a Hybrid Deep Learning-Based Intrusion Detection for Edge Computing Using Starfish Optimization Algorithm (HDLID-ECSOA) technique. The main goal of the HDLID-ECSOA technique is to provide intelligent edge computing in smart cities using advanced optimization models. Initially, the data pre-processing employs the min-max normalization to convert and standardize raw data to improve the efficiency of models. Furthermore, the dingo optimizer algorithm (DOA) technique detects and chooses the most relevant features from input data. Moreover, integrating a convolutional neural network and bidirectional gated recurrent unit with a cross-attention mechanism (CNN-BiGRU-CrAM) technique is implemented for the classification process. To enhance model performance, the starfish optimization algorithm (SFOA) is used for hyperparameter tuning to select the optimal parameters for improved accuracy. A comprehensive experimentation analysis of the HDLID-ECSOA model is performed under the Edge-IIoT and ToN-IoT datasets. The experimental validation of the HDLID-ECSOA model portrayed superior accuracy values of 99.35% and 99.33% over existing techniques under the dual dataset.