International Journal of Scientific Research and Engineering Development

People are online all the time now, and that just makes things easier for cybercriminals. Phishing emails, dodgy websites, or a homepage that suddenly looks like it was hacked—they’re everywhere. What really gets under most people’s skin is how these attacks hide behind everyday-looking links. They seem perfectly normal until you click, and suddenly you’re staring at a page just waiting to steal your bank details, passwords, or whatever else you meant to keep to yourself. Most folks can’t tell the difference between a safe link and a scam, and that’s really why online fraud keeps going up. That’s exactly why we’re building this project. It’s a machine learning tool that checks sketchy links before you get burned. It doesn’t just skim the URL—this thing looks at the length, weird symbols, sketchy domain names, HTTPS or not, scammy-sounding keywords, the whole lot. We train the model to find all those trouble signs, then it puts each URL into buckets like safe, phishing attempt, or defacement. The tool itself is just a web app. Drop in a link, hit check, and in seconds you get an answer: good to go, or risky. You even see a risk score, so you know if it’s best to run the other way. If it's especially bad, you get an alert on the spot. On top of that, there’s more—like digging into a site’s background, watching for strange patterns, and tracking URLs in real time, so nothing slips by. It’s all run through an easy dashboard, so you see the latest scans, what threats are out there, and anything new the system flags. With machine learning and real-time tracking, it’s not just waiting for trouble—it actually goes out and finds it before it hits

Shifa Bilal Tamboli, Simeen Phiroj Mulani, Arman Tajuddin Shiakh,"Suspicious URL Checker with Cloud ML" International Journal of Scientific Research and Engineering Development, V9(2): Page(2132-2138) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.