Classification of Phishing Websites
We have a dataset with meta information on 5000 trustworthy and 5000 phishing sites. • A semantic attack known as phishing lures a victim into clicking on a link or opening an attachment in an email or instant message by seeming to be a reputable organisation. Phishing is frequently used to steal valuable user data, such as login passwords and credit card details. This is a big dataset with plenty of meta data, thus before working with the dataset, you might need to understand what the meta data signify.
In order to develop a machine learning model, we first utilise a RandomForestClassifier model and train it using data from phishing sites. There is a wealth of information available in the sites' meta data that aids in identifying phishing sites. We will learn how to choose features in this particular project so that we can utilise them to train the model.