orth; users@spamassassin.apache.org
> Subject: RE: Avoiding Bayes Poison
>
> Martin, not sure how/what pastebin. Sorry. Here it is zipped though.
>
> Instructions to pastebin?
>
> Thanks,
> Clay
>
> >>> On 1/11/2007 at 10:52 AM, in message
> <[EMAIL PROTECTED
al Message-
> From: Clay Davis [mailto:[EMAIL PROTECTED]
> Sent: 11 January 2007 14:58
> To: users@spamassassin.apache.org
> Subject: Avoiding Bayes Poison
>
> Over the past several months I have been saving the spam that slips
> through to my users accounts to train my baye
Clay Davis wrote:
Thanks, Michel. How do you correct? Run it back through as ham?
C
All my user accounts have system-created "ConfirmedSpam" and "ConfirmedNotSpam"
folders. If the SA system makes a mistake, they just drag-and-drop the email into the right folder. Every
night, the
44 (0)1865 842300
> -Original Message-
> From: Clay Davis [mailto:[EMAIL PROTECTED]
> Sent: 11 January 2007 15:44
> To: Martin.Hepworth; users@spamassassin.apache.org
> Subject: RE: Avoiding Bayes Poison
>
> No its all kinda like the attached.
> C
>
> >&
Thanks, Michel. How do you correct? Run it back through as ham?
C
>>> On 1/11/2007 at 10:32 AM, in message <[EMAIL PROTECTED]>,
Michel R Vaillancourt <[EMAIL PROTECTED]> wrote:
Clay Davis wrote:
> Over the past several months I have been saving the spam that slips
> through to my users accounts
nr Systems Administrator
Solid State Logic
Tel: +44 (0)1865 842300
> -Original Message-
> From: Clay Davis [mailto:[EMAIL PROTECTED]
> Sent: 11 January 2007 14:58
> To: users@spamassassin.apache.org
> Subject: Avoiding Bayes Poison
>
> Over the past several months I h
Clay Davis wrote:
Over the past several months I have been saving the spam that slips
through to my users accounts to train my bayes with. I notice that
lately almost all of it has (what I am assuming to be) an attempt to
poison my bayes (a bunch of valid words put together in a nonsensical
p
58
> To: users@spamassassin.apache.org
> Subject: Avoiding Bayes Poison
>
> Over the past several months I have been saving the spam that slips
> through to my users accounts to train my bayes with. I notice that
lately
> almost all of it has (what I am assuming to be) an attempt
Well if you are learning it as spam and not ham then it will push up
the probablity of the words contained in the spam. So mail with those
words is most likely to be affected with Bayes. so you may want to
reduce the score of the bayes rules if you think they are not going to
be accurate. Or start
Over the past several months I have been saving the spam that slips
through to my users accounts to train my bayes with. I notice that
lately almost all of it has (what I am assuming to be) an attempt to
poison my bayes (a bunch of valid words put together in a nonsensical
paragraph) at the bottom
10 matches
Mail list logo
