Artificial intelligence-driven cybersecurity system for internet of things using self-attention deep learning and metaheuristic algorithms

Recently, Internet of Things (IoT) usage has increased rapidly, and cybersecurity concerns have also improved. Cybersecurity attacks are exclusive to the IoT, which has unique limitations and characteristics. Considering that many attacks and threats are being presented daily against IoT. So, it is significant to recognize these kinds of attacks and discover solutions to alleviate their risks. The modern approach to cybersecurity comprises the application of artificial intelligence (AI) to develop complex models for protecting systems and networks, specifically in IoT environments. Cyber attackers have also adapted by leveraging AI technologies, using adversarial AI to execute advanced cybersecurity threats. This constant evolution of AI-driven threats and defences necessitates developing more robust, adaptive, and real-time cybersecurity models to stay ahead of increasingly advanced attacks. This paper presents an Intelligent Cybersecurity System Using Self-Attention-based Deep Learning and Metaheuristic Optimization Algorithm (ICSSADL-MHOA). The proposed ICSSADL-MHOA model aims to enhance a robust cybersecurity system in IoT networks. At first, the data normalization stage employs min-max normalization to ensure consistency, accuracy, and efficiency by organizing data into a standardized format. Furthermore, the improved tuna swarm optimization (ITSO) model is implemented for the feature selection process to detect the most relevant features in the data. Besides, the proposed ICSSADL-MHOA model utilizes the bidirectional long short-term memory with self-attention (BiLSTM-SA) model for the detection and classification method of cybersecurity. Finally, the parameter selection of the BiLSTM-SA technique is performed by employing the hunger games search (HGS) technique. Comprehensive studies under the ToN-IoT and Edge-IIoT datasets validate the efficiency of the ICSSADL-MHOA method. The experimental validation of the ICSSADL-MHOA method illustrated a superior accuracy value of 99.37% over existing techniques.