AUTOMATED COLLECTION OF BRANDED TRAINING DATA FOR SECURITY AWARENESS TRAINING

摘要

A computer- implemented method of collecting training data related to a branded phishing Uniform Resource Locator (URL) may comprise retrieving a phishing URL impersonating a brand from a source of URLs; fetching a final webpage referenced by the retrieved URL; determining the main language of the textual content of the fetched final webpage; rendering one or more graphical representation of the fetched final webpage; extracting, from the source of URLs, information including the retrieved phishing URL, a brand, a type and a date associated with the retrieved phishing URL and storing the extracted information together with the fetched final webpage, a determined main language and the rendered graphical representation(s) of the fetched final webpage. A message that contains a URL matching the retrieved phishing URL may then be retrieved from a source of messages. The main language of the textual content of the retrieved message may be determined and graphical representations thereof may be rendered. A record in a database may be updated with the message, the main language of the message, and the rendered graphical representations of the retrieved message. The stored extracted information and the updated record may then be made accessible as training data to train end users to recognize phishing websites and phishing messages.