You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@spamassassin.apache.org by Claudia Burman <cb...@elbolson.com> on 2006/07/08 16:59:38 UTC
percentage of spam getting through
Hi, I'm new to the list and I guess this question was asked many times,
but I can't find this in the archives.
I use spamassassin (last perl version, updated it last week) on a mail
server, called from amavisd-new. I've set the $sa_kill_level_deflt to
5.00, if I lower this I get too many false positives.
I haven't touched any of the rules. I regularly train the bayesian filter
with false negative messages. I'm using local tests only.
My statistics show that only 60-65% of the spam messages are correctly
tagged as spam. I would like to hear from another spamassassin users if
they get similar figures.
Thanks. Sorry for my English.
Claudia Burman
El Bolson, Patagonia Argentina
Re: percentage of spam getting through
Posted by Marc Perkel <ma...@perkel.com>.
Claudia Burman wrote:
> Gary V wrote:
>
>>> I use spamassassin (last perl version, updated it last week) on a mail
>>> server, called from amavisd-new. I've set the $sa_kill_level_deflt to
>>> 5.00, if I lower this I get too many false positives.
>>> I haven't touched any of the rules. I regularly train the bayesian
>>> filter
>>> with false negative messages. I'm using local tests only.
>>
>>
>>> Claudia Burman
>>
>>
>> Why are you using local tests only?
>>
>> Gary V
>>
>> _________________________________________________________________
>> Don’t just search. Find. Check out the new MSN Search!
>> http://search.msn.click-url.com/go/onm00200636ave/direct/01/
>>
>>
> Well, I have enabled network tests and the server load got too high,
> so I disabled razor and pyzor. Now server load is acceptable and spam
> caught is about 95%!
> Thanks to all.
>
> Claudia
>
For what it's worth on my system far less than 1% of spam gets through.
Re: percentage of spam getting through
Posted by Claudia Burman <cb...@elbolson.com>.
Gary V wrote:
>> I use spamassassin (last perl version, updated it last week) on a mail
>> server, called from amavisd-new. I've set the $sa_kill_level_deflt to
>> 5.00, if I lower this I get too many false positives.
>> I haven't touched any of the rules. I regularly train the bayesian
>> filter
>> with false negative messages. I'm using local tests only.
>
>
>> Claudia Burman
>
>
> Why are you using local tests only?
>
> Gary V
>
> _________________________________________________________________
> Don’t just search. Find. Check out the new MSN Search!
> http://search.msn.click-url.com/go/onm00200636ave/direct/01/
>
>
Well, I have enabled network tests and the server load got too high, so
I disabled razor and pyzor. Now server load is acceptable and spam
caught is about 95%!
Thanks to all.
Claudia
Re: percentage of spam getting through
Posted by Gary V <mr...@hotmail.com>.
>I use spamassassin (last perl version, updated it last week) on a mail
>server, called from amavisd-new. I've set the $sa_kill_level_deflt to
>5.00, if I lower this I get too many false positives.
>I haven't touched any of the rules. I regularly train the bayesian filter
>with false negative messages. I'm using local tests only.
>Claudia Burman
Why are you using local tests only?
Gary V
_________________________________________________________________
Dont just search. Find. Check out the new MSN Search!
http://search.msn.click-url.com/go/onm00200636ave/direct/01/
Re: percentage of spam getting through
Posted by QQQQ <qq...@usermail.com>.
Are you using the URIBLs? You should be doing better than that.
QQQQ
----- Original Message -----
From: "Claudia Burman" <cb...@elbolson.com>
To: <us...@spamassassin.apache.org>
Sent: Saturday, July 08, 2006 8:59 AM
Subject: percentage of spam getting through
| Hi, I'm new to the list and I guess this question was asked many times,
| but I can't find this in the archives.
| I use spamassassin (last perl version, updated it last week) on a mail
| server, called from amavisd-new. I've set the $sa_kill_level_deflt to
| 5.00, if I lower this I get too many false positives.
| I haven't touched any of the rules. I regularly train the bayesian filter
| with false negative messages. I'm using local tests only.
| My statistics show that only 60-65% of the spam messages are correctly
| tagged as spam. I would like to hear from another spamassassin users if
| they get similar figures.
|
| Thanks. Sorry for my English.
|
| Claudia Burman
| El Bolson, Patagonia Argentina
|
|
Re: percentage of spam getting through
Posted by Loren Wilton <lw...@earthlink.net>.
> I haven't touched any of the rules. I regularly train the bayesian filter
> with false negative messages. I'm using local tests only.
> My statistics show that only 60-65% of the spam messages are correctly
> tagged as spam. I would like to hear from another spamassassin users if
> they get similar figures.
I think many users if not most users are using some extra rules and also
running at least some net tests. Using some of the rules from
www.rulesemporium.com can help quite a lot with the newrt image-only spams
that are becoming quite popular. Using some of the assorted uribl type of
net tests can also help a very large amount.
I think most SA users that have net tests enabled and some SARE (rules
emporium) rules are probably getting well over 90% spam catch rates with
very few if any false positives.
IKn addition to training Bayes with FN messages, you should regularly feed
it a little ham and a little spam, just to keep reminding it what each one
looks like. Training on FNs will improve the hits on these, but won't
necessarily improve how Bayes does in general on spam. Almost all of your
spam should be hitting Bayes_80 or better. If not, feed it some more
representative spam. Also, most of your ham should be very close to
bayes_00.
Loren