[Spambayes] SpamBayes as a gatway solution

[David Bear]

On Wed, Aug 27, 2003 at 11:45:51AM -0400, Itamar Rosenn wrote:
> Hello,
> 
> In Paul Graham's article as well as elsewhere where bayesian spam filtering
> is discussed, I've noticed the claim that SpamBayes's technique would not be
> effective as a gateway solution.

what are the 'learning' options here?  The strength of a client based
spam filter is that the user gets to train it.  Moreover, the power of
spambayes as it has been implemented for Outlook is that it
continually learns.

Switch to server/gateway mode.  Who trains it?  Lets say you have a
vigilant sys admin that does the training using VERY conservative and
CLEARLY SPAMISH email.  Okay.  Still, there WILL bo a corpus the end
users will want to 'include' in the training set.  So, you still end
up needing client side 'something'. 

On the other hand, if you stick with the vigilant and conservative
system admin, you have something like "The Spammish Inquisition".
Great idea..  A filter on the MTA that will 'slow' or sqelch the
bandwidth a spammer has.  Now, thats a powerfull idea.

> 

-- 
David Bear
phone: 	480-965-8257
fax: 	480-965-9189
College of Public Programs/ASU
Wilson Hall 232
Tempe, AZ 85287-0803
 "Beware the IP portfolio, everyone will be suspect of trespassing"