Friday, 3 November 2006

Image Spam on the Rise, says Secure Computing

Secure Computing is all set to wag war against image Spam, where spammers hide messages in image files to escape detection. Over the past few months, Secure Computing Research has identified a 200-percent increase in the amount of image Spam, which today accounts for 30 percent of all Spam and approximately one in every four messages circulating on the Internet.

"Image-based Spam is a particularly difficult problem for a couple of reasons," noted Michael Osterman, founder and principal of Osterman Research. "It is much harder to detect with conventional Spam-filtering and blocking technologies. Further, it is typically much larger than normal text-based Spam, consuming much more bandwidth and storage."

"Traditional anti-Spam software depends on content filtering techniques such as keyword filtering and Bayesian analysis to detect Spam. Even the technology used to recognise characters from images, Optical Character Recognition (OCR), is not effective on today's image Spam," said Dr. Paul Judge, chief technology officer of Secure Computing. "Spammers are using advanced mathematical and graphical techniques like random modification of image pixels and dynamic construction of images from multiple components to bypass Spam filtering tools."

Organisations cannot afford to depend solely on localised protection using algorithms that quickly become obsolete and cannot accurately filter new threats like image Spam. Secure Computing has evolved its TrustedSource engine to detect and block traffic from illegitimate sources using a global reputation approach. TrustedSource collects information on e-mail senders and the types of e-mail they generate by accumulating data from more than 7000 sensors located in 48 countries. As it gets more data, the breadth and depth of the TrustedSource database increases, accurately categorising sender reputations for multiple identities including IP, domain and URL reputations. This approach has proven effective to proactively delete image Spam before it hits the corporate mail server, the company claims.