SECURE QR CODE SCANNER TO DETECT MALICIOUS URL USING MACHINE LEARNING

Abstract

Q-R codes are utilised for a variety of purposes, including accessing online webpages and making a settlement. The Internet facilitates a wide range of illegal acts, including unsolicited e-marketing, financial embezzlement, and malicious distribution. Even though all the users identify the presence of Q-R codes visually, the information stored in those codes can only be accessed through an allocated Q-R code decoder. Q-R codes have also been shown to be used as an effective attack vector, For example techniques include social engineering, phishing, pharming, etc. Harmful codes are distributed under false pretences in congested areas, or malicious Q-R codes are pasted over current ones on billboards. Finally, consumers rely on decoder operating system to determine a random Q-R code is whether malicious or benign. For the purpose of this report, we consider the identification of malicious Q-R codes as a two-way classification problem in this research, and we test the effectiveness of many well-known M-L algorithms, including namely K-Nearest Neighbour, Random Forest, Binary LSTM and Support Vector Machine. This implies that the proposed method might be deemed an optimal and user- friendly QR code security solution. We created a prototype to test our recommendations and found it to be secure and usable in protecting users from harmful QR Codes