Towards a formatting-based spam filter

The spammers’ biggest strength – their ability to adapt quickly to new filtering methods – hides one of their most important weaknesses, the inability to change certain aspects of the message. such as the spam layout, the way a message “looks”.

Unfortunately, so far this topic attracted little research, if any, possibly because some spam e-mails have no significant layout differences from legit mail.

However, formatting, either plain text or html, is a valuable source of information for certain types of email, such as most newsletters, phishing e-mails or nigerian scams. These could be singled out by onsidering this criterion.

The massive text and standard signatures of the 419 – nigerian – scams, the multitude of links and addresses in newsletters, the logos in phishing messages are only a few examples of obvious visual identifying items widely known. But, though widely encountered and full of valuable information, these patterns are, to the best of our knowledge, scarcely used in identifying email type. We’re working on correcting this ommission.

About the author


Razvan Stoica is a journalist turned teacher turned publicist and technology evangelist. When Bitdefender isn't paying him to bring complex subjects to wide audiences, he enjoys writing fiction, skiing and biking. Razvan Stoica started off writing for a science monthly and was the chief editor of a science fiction magazine for a short while before moving on to the University of Medicine in Bucharest where he lectured on the English language. Recruited by Bitdefender in 2004 to add zest to the company's online presence, he has fulfilled a bevy of roles within the company since. In his current position, he is primarily responsible for the communications and community-building efforts of the Bitdefender research and technology development arm.

Add Comment

Click here to post a comment