Toward Hybrid Deep Learning-Based Threat Detection With Blockchain Technology For Secure Iot-Based Consumer Electronics

Consumer electronics is a device designed to meet the everyday needs of individuals, including home appliances, smartphones, and laptops. The Internet of Things (IoT) environment is witnessing tremendous growth, driven by the simultaneous increase and continuous cyber-attack innovation. The imperative to fortify IoT devices against emerging threats became more prevalent as these threats became increasingly complex. In this context, threats include malware attacks, unauthorized access, and data breaches. Securing these devices requires robust encryption, regular software updates, and vigilant monitoring to protect sensitive information and ensure user safety. Threat detection using deep learning (DL) includes leveraging cutting-edge neural network models to detect and alleviate security threats within digital environments. DL, a branch of machine learning (ML), excels in processing abundant data to detect anomalies and patterns that might indicate possible threats. This technique improves classical threat detection techniques by reducing false positives and enhancing accuracy. By continuously analyzing data from various sources, such as network traffic and user behavior, DL techniques can quickly recognize and respond to emerging vulnerabilities, providing a proactive and adaptive security solution essential for protecting consumer electronics and IoT devices. This study develops a new Hybrid DL-based Threat Detection with Blockchain Technology (HDLTD-BCT) technique for secure IoT-based consumer electronics. The presented HDLTD-BCT technique can improve security among consumer electronics in the IoT environment. For this purpose, the HDLTD-BCT technique initially applies BC technology to monitor data flow in the IoT platform. The HDLTD-BCT technique scales the input data for threat detection using a min–max scalar. Besides, the detection process is performed by HDL, comprising a stacked LSTM-based denoising autoencoder (LSDAE) model. To enhance the HDL method’s performance, the Maritime Cyber Warfare Officers (MCWO) performs the hyperparameter selection process. The experimental results of the HDLTD-BCT technique can be validated utilizing the NSLKDD dataset. The simulation outcomes of the HDLTD-BCT technique exhibited a superior accuracy value of 99.68% compared to other DL models.