[Spambayes] SpamBayes to Handle Embedded Images
wsy at merl.com
Sun Oct 2 21:20:23 CEST 2005
From: <FreeMJ at hotpop.com>
Back in April, Tony Meyer posted that he was receiving a lot of image-based
I too am having nothing but trouble with embedded images:
- Daily adds for fake Rolex watches
- Daily stock tips
- TONS of drugs for sale.
This style of Spam contains an image at the top, followed by a bunch of
totally unrelated text that has been copied from some kind of random
composition. I have very large Spam & Ham folders, that I've successfully
trained SpamBayes with. It's only these image-based adverts that sneak by
EVERY DAY. Something really needs to be done about this type of Spam within
SpamBayes. Are any other Spam engines able to handle this stuff, by
scanning the image for text, or something?
I'm not having trouble with it, because nobody sends me gifs or
jpgs in the mail. Thus, any that appear are almost certainly
Do you have people sending you a lot of images that _aren't_ spam?
If not, then train the images as spam. It won't matter if the
images can be decoded or not; just establish a liklihood that any
image at all means it's a spam.
I'm using CRM114, but it shouldn't matter what engine you use, at least
in the near term, as long as you don't get a lot of images otherwise.
More information about the SpamBayes