Spam email hawking miracle pills and targeting the gullible with tales of offshore bank accounts containing untold fortunes used to be mostly text-based but spammers have turned to using images embedded in the email to outwit existing spam filtering programs.
Researchers at Concordia University in Montreal say a new statistical framework for spam filtering can quickly and efficiently block unwanted messages.
"The majority of previous research has focused on the textual content of spam emails, ignoring visual content found in multimedia content, such as images," doctoral candidate Ola Amayri said.
"By considering patterns from text and images simultaneously, we've been able to propose a new method for filtering out spam," she said.
New spam messages often employ sophisticated tricks such as deliberately obscuring text, combining words with symbols and using groups of the same images with different backgrounds and colors that might contain random text.
"Spammers keep adapting their methods so that they can trick the spam filters," Amayri said.
Traditional spam filters are powerless to stop such messages because they normally focus on either text or images but rarely both, she said.
"Our new method for spam filtering is able to adapt to the dynamic nature of spam emails and accurately handle spammers' tricks by carefully identifying informative patterns, which are automatically extracted from both text and images content of spam emails."