Intelligent Fraud Detection in IoT-Driven Transactions Using Multi-Layer Neural Classification

Abstract

When individuals conduct financial fraud in an Internet of Things (IoT) environment, it is because they have stolen the identity of another person or their credit card information and then utilised it to make fraudulent mobile transactions. Within the context of the IoT, financial fraud is a problem that is rapidly developing as a result of the growth of smartphones and internet transition services. Because financial fraud leads to monetary loss, it is necessary to have a system that is accurate for identifying financial fraud in an IoT environment. This is because financial fraud occurs in the real world. In the context of the IoT, there is an urgent requirement for a trustworthy system that can identify instances of financial fraud. This is because the use of smartphones and online transactions has become increasingly widespread. Our proposed method, which makes use of deep multi-layer classification, is comprised of two essential steps: first, we need to identify the presence of an intrusion; second, we need to identify the sort of intrusion that has occurred. In order to efficiently extract features, we make use of a technique known as Synthetic Minority Oversampling Technique (SMOTE), which results in an improvement in the classification accuracy. The foundation of our research is the utilisation of a Multiple-hidden Layer Backpropagation Neural Network (BPNN) for the purpose of distinguishing between routine operations and actions that include intrusion. Considering the multi-pronged approach ensures any potential risks is achieved. By merging these approaches into a robust and accurate fraud detection system, we have made a substantial contribution to the field.