Spam in images
Eric Wood
eric at interplas.com
Wed Sep 6 19:46:51 CEST 2006
----- Original Message -----
From: "Tom Anderson"
> The email's "random" text was more damning though, with terms like
> "cried", "wont", "quarrelsome", etc., apparently not showing up in my
> hams very often at all. But perhaps even more surprisingly, bogofilter
> is apparently already filtering inline images for me, with "mime:gif",
> "head:type", "mime:image", "mime:Content-ID", and "head:related" all
> very spammy. So there's not much reason to add additional filtering in
> this regard anyway!
Umm. The way I read you is that your promotion for people to use inline
images will yield a high spammy result. Having bogofilter train on image
spam will cause poisoning and eventual false positives.
For example, one current problem I have is that my users have recently asked
for their Ebay passwords to be changed. Ebay sends them an email
confirmation in which the user never gets. This is because bogofilter saw
it as spam. This is because of all the "fishing" scam emails look exactly
like an official Ebay message including all the verbage and all but one
legit url. Bogofilter trained (thanks to -u) on all these slightly various
fishing emails. Now, when the legit email comes in - it can't help but
classify it as spam.
This "token poisoning" isn't a big deal for me yet. And I don't want it to
get bad. But I fear that if I train bogofilter on image spams, I'll be
caught in a never ending cycle of re-training. I rarely do any training.
Hey, I'm with you and I'm not arguing or anything. I honestly do challenge
my own thought processes and am open to other ideas.
-eric wood
More information about the Bogofilter
mailing list