To create a lightweight representation of URLs, a dataset composed of 52,000 URLs were collected:

• 26,000 were taken from the Alexa Top website and labelled as Legitimate. For obtaining the legitimate URLs, the domains have been passed through a Heritrix web crawler to extract the URLs, and later, the extracted URLs were checked through VirusTotal to filter the benign URLs.

• 26,000 URLs were obtained from PhishTank and were labelled as Phishing.