Bayes is also only as good as what you are teaching it.  You must ensure
that you teach is hams that apply to your business and/or customers.
The $85885 spammers got into a bayes very shortly after we started
receiving them.



-----Original Message-----
From: Scot L. Harris [mailto:[EMAIL PROTECTED] 
Sent: Saturday, July 03, 2004 3:36 PM
To: Spamassasin Users List
Subject: Re: Bayes less effective over time?

On Sat, 2004-07-03 at 17:58, Jack L. Stone wrote:
> The point about less effective is the question of "weight". As you
know,
> the spammer changes the form of attack constantly in an effort to get
> around our defenses. Thus, if your "basket" is full of apples and now
there
> are more "oranges" being used than apples, the defeneses are weaker.

But I thought that was the point of the bayes system.  You keep teaching
a sampling of the current spam and ham you get and it expires older
entries as they exceed a certain time period.  Which in itself tells me
that the spammer could then go back to their "old" tricks and get around
the defenses until the system re-learns those tricks.  
-- 
Scot L. Harris
[EMAIL PROTECTED]

...this is an awesome sight.  The entire rebel resistance buried under
six
million hardbound copies of "The Naked Lunch."
- The Firesign Theater 


Reply via email to