IWETHEY v. 0.3.0 | TODO
1,095 registered users | 0 active users | 0 LpH | Statistics
Login | Create New User
IWETHEY Banner

Welcome to IWETHEY!

IWETHEY Home / IWETHEY Board / Theory and Practice of Programming Forum / Bayesian filters.
Post #221,043
by Another Scott
8/26/05 9:35:58 AM
Reply
New Bayesian filters.
I think it's a solved problem. If you've got 10M users and they all get the same message (or one that's slightly different), it's a good bet that it's spam. ;-) Bayesian filters can be trained to reject such things.

SpamAssassin has various [link|http://systems.cs.uoregon.edu/Solaris/spamassassin.php|rules] regarding images.

I'm reasonably sure this problem has been solved. But I'm no expert. If it's continuing to concern you, check the archives of the [link|http://wiki.apache.org/spamassassin/MailingLists|SpamAssassin mailing list] or ask there. They should know.

HTH. Luck!

Cheers,
Scott.
Post #221,047
by boxley
8/26/05 9:59:59 AM
Reply
New actually I hang out here
[link|http://www.maawg.org/home/|http://www.maawg.org/home/] and spamm assasin is the engine that a lot of vendors use but the slippage is increasing concerning images.
thanx,
bill
"the reason people don't buy conspiracy theories is that they think conspiracy means everyone is on the same program. Thats not how it works. Everybody has a different program. They just all want the same guy dead. Socrates was a gadfly, but I bet he took time out to screw somebodies wife" Gus Vitelli

Any opinions expressed by me are mine alone, posted from my home computer, on my own time as a free american and do not reflect the opinions of any person or company that I have had professional relations with in the past 49 years. meep
questions, help? [link|mailto:pappas@catholic.org|email pappas at catholic.org]
     text decoding from images - (boxley) - (9) - Aug. 25, 2005, 12:41:15 PM EDT
         Block HTML emails at the server. >;) -NT - (Steve Lowe) - Aug. 25, 2005, 12:45:06 PM EDT
         Bayesian filters - (Yendor) - (1) - Aug. 25, 2005, 12:45:22 PM EDT
             using them, not as effective as they used to be - (boxley) - Aug. 25, 2005, 12:52:46 PM EDT
         Hmm - (broomberg) - Aug. 25, 2005, 12:56:57 PM EDT
         GAH! old timers disease - (boxley) - (4) - Aug. 25, 2005, 10:24:28 PM EDT
             Hasn't this problem been solved? - (Another Scott) - (3) - Aug. 25, 2005, 10:43:02 PM EDT
                 tell me how I determine what is unsoliceted - (boxley) - (2) - Aug. 26, 2005, 08:43:13 AM EDT
                     Bayesian filters. - (Another Scott) - (1) - Aug. 26, 2005, 09:35:58 AM EDT
                         actually I hang out here - (boxley) - Aug. 26, 2005, 09:59:59 AM EDT

Aw, good for him.
81 ms