using sa-learn on spam attachements

Greg Matthews gmatt at NERC.AC.UK
Thu Sep 15 09:58:59 IST 2005

On Tue, 2005-09-13 at 14:08 -0500, Alex Neuman wrote:
> You could try using the archive option to store the mails, unprocessed, 
> at least for a while. That way you have something to feed SA with.

except the most important reason for training the bayes database is for
cases where MS/SA have got it wrong.

I'm still trying to find a good solution to this problem - aside from
employing someone full time to go through all false positives/negatives,
strip them down and feed them through!


Greg Matthews           01491 692445
Head of UNIX/Linux, iTSS Wallingford

------------------------ MailScanner list ------------------------
To unsubscribe, email jiscmail at with the words:
'leave mailscanner' in the body of the email.
Before posting, read the Wiki ( and
the archives (

Support MailScanner development - buy the book off the website!

More information about the MailScanner mailing list