Artificial Neural Network-Based Malware Detection Model Among Shopping Apps to Increase the App Security

Abstract

Even though there are many reliable online merchants these days, scammers can still prey on unsuspecting clients by using the Internet's anonymity. Using the most latest technologies, scammers produce fraudulent retailer apps that mimic genuine online retail sites. They might utilize complex patterns and designs. Numerous of these applications provide exceptionally inexpensive prices on premium goods including renowned jewelry, clothing, and technology companies. Sometimes you might receive what you paid for, but it might be a fake or you might not receive anything at all. Money orders, pre-loaded cards, and wire transfers are common payment methods requested by con artists, but it is doubtful that you will receive your order or see your money again if you send it this way. Con artists frequently ask for money orders, pre-loaded cards, and wire transfers as payment, but it is unlikely that you will receive your order or see your money again if you send it this way. Social networking sites are now being used to establish fake online storefronts in a more recent iteration of online retail scams. They briefly launch the company and frequently sell counterfeit trademark jewelry or clothing. Several sales later, the stores are gone. Because they also use social media to promote their fake app, we shouldn’t believe something just because we have seen it advertised or shared there. There is a need to mark these submissions. The experiment's fundamental pillars are three dimensions: feature extraction, selection, and malware prediction.