VBQ-Net: A Novel Vectorization-Based Boost Quantized Network Model for Maximizing the Security Level of IoT System to Prevent Intrusions

Abstract

Data sharing with additional devices across wireless networks is made simple and advantageous by the Internet of Things (IoT), an emerging technology. However, IoT systems are more susceptible to cyberattacks because of their continued growth and technological advances, which could lead to powerful assaults. An intrusion detection system is one of the key defense mechanisms for information and communications technology. The primary shortcomings that plague current IoT security frameworks are their inability to detect intrusions properly, their substantial latency, and their prolonged processing time and delay. Therefore, this work develops a clever and innovative security architecture called Vectorization-Based Boost Quantized Network (VBQ-Net) for protecting IoT networks. Here, a Vector Space Bag of Words (VSBW) methodology is used to reduce the dimensionality of features and identify a key characteristic from the featured data. In addition, a brand-new classification technique, called Boosted Variance Quantization Neural Networks (BVQNNs), is used to classify the different types of intrusions using a weighted feature matrix. A Multi-Hunting Reptile Search Optimization (MH-RSO) algorithm is employed during categorization to calculate the probability value for selecting the right choices while anticipating intrusions. In this study, the most well-known and current datasets, such as IoTID-20, IoT-23, and CIDDS-001, are used to validate and evaluate the effectiveness of the proposed methodology. By evaluating the proposed approach on standard IoT datasets, the study seeks to address the limitations of current IoT security frameworks and provide a more effective defense mechanism against cyberattacks on IoT systems.