Phishing Website Detector Website Phishing costs internet users billions of dollars per year. Phishers steal personal information and financial account details such as usernames and passwords, leaving users vulnerable in the online space.

Project Source and Insipiration: https://towardsdatascience.com/whataphish-detecting-phishing-websites-e5e1f14ef1a9

https://archive.ics.uci.edu/ml/datasets/Phishing+Websites#

In this project, we built Phishing Website Detector - a mechanism to detect phishing websites. Our methodology uses not just traditional URL based or content based rules but rather employs the machine learning technique to identify not so obvious patterns and relations in the data. We have used features from various domain spanning from URL to HTML tags of the webpage, from embedded URLs to favicon, and databases like WHOIS, Alexa, Pagerank, etc. to check the traffic and status of the website. We were able to obtain an accuracy of more than 96%, recall greater than 96% with a False Positive Rate of less than 5%, thus classifying most websites correctly and proving the effectiveness of the machine learning based technique to attack the problem of phishing websites. We provided the output as a user-friendly web platform whch can futher be extended to a browser extension to provide safe and healthy online space to the users.