Detecting Known and New Salting Tricks in Unwanted Emails

Spam and phishing emails are not only annoying to users, but are a real threat to internet communication and web economy. The fight against unwanted emails has become a cat-and-mouse game between criminals and people trying to develop techniques for detecting such unwanted emails. This paper describes a framework to identify email messages that might contain new, previously unseen tricks. To this end, it compares the simulated perceived email message text generated by hidden salting simulation system to the OCRed text it obtained from the rendered email message. It presents robust text comparison techniques and train a classifier based on the differences of these two texts.