Enhancing Malicious QR Code Link Detection with Swarm-Intelligent Squirrel-Search Optimized ANN

Recently, hackers have made plans to replicate harmful links by tricking people in a variety of ways. By acquiring access to sensitive information they use online, they attempt to remotely manipulate the victims' machines or obtain their data. QR codes are two-dimensional barcodes that can encode different types of data and are viewable by digital devices like smart phones. However, there is no recognized procedure for creating QR codes; therefore they could be vulnerable to a number of dubious assaults. The goal of this study is to use the Swarm-Intelligent Squirrel-Search Optimized Artificial Neural Network (SISSO-ANN) to identify harmful URLs concealed behind 2D QR codes. On the basis of barcode forgery, a cyber attack that may be carried out online has been proposed. Through a number of sites, a dataset of harmful and helpful Uniform Resource Locators (URLs) was produced, and their lexical properties were gathered. The experimental finding demonstrates that SISSO-ANN works better than other current techniques and achieves detection precision value of 93.80%,and accuracy of 93.50% which is much greater than the present secure QR code scanners. Additionally, the application with the least privilege authorization, SISSO-ANN, is the most privacy-friendly.