BPSO-AHDL-IDS: Binary Particle Swarm Optimization-Based Automated Hybrid Deep Learning Model for Intrusion Detection of Internet of Things

The pervasive adoption of Internet-of-Things (IoT) systems has exposed critical vulnerabilities in cyber-security frameworks due to their decentralized deployment in unattended environments. While deep learning-based intrusion detection systems (IDSs) offer promising solutions, the design of hyper-parameters and neural architectures in existing models imposes prohibitive computational costs and expert dependency. To address these limitations, this work proposes an innovative automated hybrid deep learning method for IDS by employing a binary particle swarm optimization (BPSO) algorithm called BPSO-AHDL-IDS to effectively address the intrusion detection tasks of IoT. In BPSO-AHDL-IDS, the combination of convolutional neural network and recurrent neural network is considered as the hybrid deep learning model to extract features of the IoT dataset for accurate detection of intrusions. First, an efficient binary encoding mechanism is developed to describe the hyper-parameters and neural architectures of the hybrid deep learning model. Then, an efficient BPSO-based evolutionary operation is introduced to evolve the hyper-parameters and neural architectures to discover the optimized hybrid deep learning model. The performance of the proposed BPSO-AHDL-IDS method is testified by employing four datasets gathered from different IoT scenarios. It achieves accuracy of 0.9832, 0.9959, and 0.9897, precision of 0.9700, 0.9788, and 0.9843, recall of 0.9724, 0.9822, and 0.965, and $F_{1}$ -score of 0.9712, 0.9804, and 0.9744 on Bot-IoT, ToN-IoT, and Gas Pipeline datasets, respectively. On SWaT dataset, it achieves a precision of 0.9962, a recall of 0.9969, and an $F_{1}$ -score of 0.9965, respectively. The experimental results show the superiority of the proposed BPSO-AHDL-IDS method to machine learning methods, state-of-the-art manually designed and automated deep learning-based IDSs in terms of accuracy, precision, recall, and $F_{1}$ -score. Note to Practitioners—The open deployment of Internet-of-Things (IoT) devices in unattended environments makes them highly vulnerable to malicious cyber-attacks. This paper proposes a novel approach to enhance the security of IoT systems through the use of automated deep learning-based intrusion detection systems (IDSs). Traditional deep learning models used in IoT security require manual setting of hyper-parameters and neural architectures, which is a time-consuming and tedious trial-and-error process that relies on experts. To overcome this limitation, we propose an automated hybrid deep learning-based IDS, called BPSO-AHDL-IDS. The BPSO-AHDL-IDS method combines the strengths of a convolutional neural network and a recurrent neural network to extract features from IoT datasets to enhance the performance of intrusion detection. An efficient binary encoding mechanism is developed to describe the hyper-parameters and neural architectures of the hybrid deep learning model. Additionally, an evolutionary operation based on a binary particle swarm optimization (BPSO) algorithm is introduced to evolve these parameters and discover the optimized hybrid deep learning model. The performance of the proposed BPSO-AHDL-IDS method is evaluated using four datasets collected from various IoT scenarios. Overall, this paper presents a promising approach to improve IoT security through the integration of automated deep learning techniques. The proposed BPSO-AHDL-IDS method offers an automated and effective solution for addressing the challenges of intrusion detection in IoT systems. Practitioners in the IoT domain can significantly benefit from adopting this approach.