Microsoft Exchange Add-On to Tackle One Front in Spam War

The Exchange Intelligent Message Filter unveiled at Comdex addresses one part of the spam problem, and enterprises will continue to need third-party software to complement its filtering capabilities, Microsoft admitted.

LAS VEGAS—Microsoft Corp. may be building greater e-mail filtering features into Exchange Server 2003, but dont expect the software giant to go it alone in the spam wars.

Microsoft officials, in an interview with eWEEK.com on Monday, said that the upcoming Exchange Intelligent Message Filter (IMF) add-on to Exchange Server 2003 that company Chairman and Chief Software Architect Bill Gates demonstrated during his Comdex keynote here on Sunday isnt designed to be the end-all, be-all solution for stopping spam within an enterprises messaging network.

"We feel most companies will run it as a complementary sort of solution," said T.A. McCann, an Exchange group product manager.

The Exchange IMF is expected to be available in the first half of 2004 for Exchange Server 2003 users under the Microsoft Software Assurance licensing program.

It incorporates Microsofts SmartScreen technology, an approach to spam filtering that Gates introduced a day earlier. SmartScreen uses a machine-learning approach developed by Microsoft Research that incorporates feedback from e-mail users themselves and is already being used with Hotmail and MSN e-mail accounts and in Outlook 2003.

/zimages/2/28571.gifTo read more about Bill Gates Comdex keynote address, click here.

A large part of the feedback for SmartScreen is coming from Microsoft Hotmail users. Microsoft early in 2003 began recruiting hundreds of thousands of Hotmail volunteers to score e-mail as either legitimate or unsolicited, said Kevin Doerr, group business manager of Microsofts anti-spam technology and strategy group. Data based on about 5 million scored messages so far is stored in a database where the SmartScreen technology can investigate the attributes of the legitimate e-mail compared to the spam e-mail for filtering.

Next page: Spam confidence level.