On Wed, Oct 25, 2006 at 10:18:44AM -0500, Bill wrote: > Ok, if the image spams all have a different hash wouldn't that make the > Hash function built into Fuzzy OCR useless as well? I'm not sure I buy into > that thinking. The hash option in my Fuzzy OCR setup runs pretty well.
I know nothing about FuzzyOCR, but it all depends on the hash function. If it deals with the differences that are introduced, then it won't have a problem with those differences. ;) > Couldn't there be an RBL established similar to DCC, Razor or Pyzor that > maintained the hash of known spam images and forego the wordlist > detection? Sure, how about DCC, Razor, and Pyzor? Razor, specifically, already looks at individual message parts. If you have a better hash algorithm for them, I'm sure they'd be happy to use it. :) -- Randomly Selected Tagline: "This isn't an office. It's Hell with fluorescent lighting." - Unknown
pgpVFHZ9yuE9G.pgp
Description: PGP signature