On Thu, 2003-06-26 at 15:27, Matt Kettler wrote:
> Unfortunately developing good rules is a very labor-intensive task. The
> 2.5x family is, at least in my opinion, slightly weaker in the rules
> department than some of its predecessors. This weakness in the rules is the
> result of the effort
On Thu, 26 Jun 2003, Matt Kettler wrote:
> At 09:48 AM 6/26/03 -0400, Jack Gostl wrote:
>
> >What really worries me is the growing number of messages between 4.5 and
> >5. Many of these already have a Bayes score of 90+.
>
> Agreed, this is why rule development for SA always has been, and always
At 09:48 AM 6/26/03 -0400, Jack Gostl wrote:
What really worries me is the growing number of messages between 4.5 and
5. Many of these already have a Bayes score of 90+.
Agreed, this is why rule development for SA always has been, and always
will be, an arms race.
Spammers are aware of SpamAssas
At 08:51 AM 6/26/03 -0400, Jack Gostl wrote:
That PGP sig buried in HTML sticks out like a sore thumb.
Even better, if you check my post from 6/14, most of these have a PGP
signature block, but are without a "begin pgp signed message" block..
Try this meta rule pair for a starter. I can't guara
On Thu, 26 Jun 2003, Matt Kettler wrote:
> At 08:51 AM 6/26/03 -0400, Jack Gostl wrote:
> >That PGP sig buried in HTML sticks out like a sore thumb.
>
>
> Even better, if you check my post from 6/14, most of these have a PGP
> signature block, but are without a "begin pgp signed message" block.
On Thursday 26 June 2003 14:51, Jack Gostl wrote:
> Bayes attack is tougher, but 3-5 lines of all lower case letters with no
> punctuation would be a good start.
It would be, if it wouldn't just trigger the next cycle of evolution: E.g.
a text generator using simple markov chains with single-word
On Thu, 26 Jun 2003, Martin Bene wrote:
> >This is becoming a regular thing. A fake PGP signature buried
> >inside HTML
> >followed by a string of random words clearly aimed at tripping up the
> >Bayes algorithms. Its becoming a daily event. See below.
>
> Yep, I've been seein these for quite so
Hi Jack,
>This is becoming a regular thing. A fake PGP signature buried
>inside HTML
>followed by a string of random words clearly aimed at tripping up the
>Bayes algorithms. Its becoming a daily event. See below.
Yep, I've been seein these for quite some time now;What I'm seeing is:
- spam in
