detcting obfuscation: html garbage tags:done normal language letter frequency:easy to do, easy to get by just modify random keyword to generate same frequency as english words. This would still catch the stupider spammers doing bayes poisoning.
Detect poisoning attempt, and reject an addition to bayes database on email that appears to be poisoning attempt. Run grammer/spellchecker, if number of mispelled words exceeds certain percentage then handle bayes differntly? Have hash of 50,000 top words and match words to letter frequency in normal email? What constitues normal email at your site? Add in additional bayesian filters such as bogofilter or crm that create their bayesian database with different algorithms. Which lowers fp and fn (slated for 2.70) http://bugzilla.spamassassin.org/show_bug.cgi?id=2301 program an AI that can read english, and hates spam. :) -- Luke Computer Science System Administrator Security Administrator,College of Engineering Montana State University-Bozeman,Montana ------------------------------------------------------- The SF.Net email is sponsored by EclipseCon 2004 Premiere Conference on Open Tools Development and Integration See the breadth of Eclipse activity. February 3-5 in Anaheim, CA. http://www.eclipsecon.org/osdn _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
