Hi, > Why do you think bayes have problems with such email? > Considering the example you put on Pastebin is triggering > "BAYES_00=-1.9" I believe that if you are able to collect > a sufficient amount of these messages and feed it to SA > through sa-learn you should start to trigger more BAYES_5X > or even BAYES_9X rules.
I think it's a problem for the reason you mentioned - perhaps it should have detected at bayes99, although it's very common language. > Since you are operating a forwarding server for other users > you can think about creating a fake account just to collect > samples such as the one you've posted. I'm actually already doing that, but there's entirely too much mail to scan each one manually. For the ones that are getting delayed, I just read them directly from the mailq then typically delete them. I'd ideally at least like a way to receive notification when this is happening, if it's not possible to block them. Thanks, Alex
