Sciweavers

Share
CEC
2003
IEEE

Increasing the accuracy of a spam-detecting artificial immune system

9 years 3 months ago
Increasing the accuracy of a spam-detecting artificial immune system
AbstractSpam, the electronic equivalent of junk mail, affects over 600 million users worldwide. Even as anti-spam solutions change to limit the amount of spam sent to users, the senders adapt to make sure their messages are seen. This paper looks at application of the artificial immune system model to protect email users effectively from spam. In particular, it tests the spam immune system against the publicly available SpamAssassin corpus of spam and non-spam, and extends the original system by looking at several methods of classifying email messages with the detectors produced by the immune system. The resulting system classifies the messages with similar accuracy to other spam filters, but uses fewer detectors to do so, making it an attractive solution for circumstances where processing time is at a premium.
Terri Oda, Tony White
Added 23 Aug 2010
Updated 23 Aug 2010
Type Conference
Year 2003
Where CEC
Authors Terri Oda, Tony White
Comments (0)
books