Re: [Asrg] REDIRECt to ASRG RE: Reputation systems

[Pete McNeil <madscientist at microneil.com>]

On Monday, August 16, 2004, 8:28:15 PM, Phillip wrote:

HBP> I think that this is getting into an ASRG question.

HBP> If we create a graph of false positives vs false negatives we get
HBP> an L shaped curve for most filtering technologies that are
HBP> parameterizable and a point for a non perameterized technology
HBP> such as a blacklist.

HBP> Rather than arguing this point round and round does anyone have
HBP> a ready made graph with the various blacklists plotted on it so
HBP> that we could make a useful comparison?

This is not precisely what you want, but it does go a long way toward
giving you the data you are after. I helped develop some of the fine
details on this. Markus Gufler and myself are using it to tune SpamChk
and Message Sniffer respectively. This particular analysis is now
produced weekly for public review. Markus can provide deeper analysis
from this system as time goes on. I am developing tools that will
allow Declude (an IMail server anti-spam/anti-virus tool) users to
generate this analysis from their systems easily so that a broader
cross-section of the data will be available. With luck this will
happen soon.

Here is a link to the analysis:

http://www2.spamchk.com/public.html

Hope this helps,
_M

Pete McNeil (Madscientist)
President, MicroNeil Research Corporation
Chief SortMonster, www.sortmonster.com




_______________________________________________
Asrg mailing list
Asrg at ietf.org
https://www1.ietf.org/mailman/listinfo/asrg