[EMAIL PROTECTED] wrote:
>
> I've been developing a spam / ham corpus from those things
> which my config of SA doesn't catch. Problem is I get these
> in Outlook, and now I want to Bayes them. How do you guys get
> your spam corpus set up? Do you just not use Outlook? Is
> there a way to get t
Chip Paswater wrote:
>
> If you use Windows and Outlook, try Cloudmark's Spamnet product. It's
> the commercial version of razor, and feeds the same backend database.
>
> I think it's still free to use. http://www.cloudmark.com
No it's not free (subscription is $1.99 a month or something) but th
Tony Earnshaw wrote:
> But my Norwegian daughter, running Win 98
> and getting her mail with Outlook Express, finds that most of her
> mail is spam and she has to pay her Norwegian ISP extra for filtering
> her mail, or pay for a commercial spam filter.
She could always use SAproxy, very easy to
MBR wrote:
> ...
> the contents
> of the "src=" attribute on the tag that fetches the image. In
> addition to the hostname and path to the image, it sends CGI arguments
> which contain MY email address! Ingenious of someone to figure out
> that CGI arguments are not limited to , and you can sen
Marek Dohojda wrote:
> As most of you know Outlook doesn't forward headers when you forward
> an e-mail (and with newer Outlook 2002+, you can't even resend with
> headers intact). Therefore Outlook is a bad tool in traning SA.
You could try SpamSource:
http://www.daesoft.com/SpamSource/index
Jonathan Nichols wrote:
> Mathew Hendry wrote:
>> Is there an easy way to detect fraudulent links like the following
>> from a recent scamspam.
>>
>> > href=3D"http://hyperiod.hypermart.net/fraud.html";>> face=3DArial=20 size=3D2>BestBuy.com/fra
Is there an easy way to detect fraudulent links like the following from
a recent scamspam.
http://hyperiod.hypermart.net/fraud.html";>BestBuy.com/fraud_department.html
i.e. both the href and the visible text look like URLs, but don't come
anywhere close (I guess that's the tricky part :) to match
Kent R. Frazier wrote:
> Everything seem to be working fine except for this one problem. I
> receive daily weather forcasts from weather.com and SpamAssassin is
> marking them as spam. I addend weather.com to my whitelist, but it is
> still being marked as spam.
>
> Here is my local.cf file:
>
>
Simon Byrnand wrote:
> At 16:38 14/06/03 +0100, Mathew Hendry wrote:
>
>> No, auto-learn learns only from mails with particularly high or low
>> scores. The default thresholds are
>>
>> auto_learn_threshold_nonspam-0.5
>> auto_learn_threshold_spam
Jim Ford wrote:
> If auto-learn is on (default setting), is there any point in putting
> correctly identified spam and ham through sa-learn? Is the only use
> for sa-learn to teach SA when spam or ham is incorrectly identified?
No, auto-learn learns only from mails with particularly high or low
s
10 matches
Mail list logo