The Next Step In Spam Filtering

simeonbeta2 writes "Paul Graham (of "A Plan for Spam" fame) has a couple of new articles up. The first one details the success of Bayesian spam filters despite various circumvention techniques by spammers. While the success of Bayesian spam filtering is encouraging, it certainly hasn't seemed to stem the flow of spam in the last year or so. His second article, however, suggests finally taking the anti-spam battle to the spammers! Paul proposes that spam filtering packages automatically spider links contained in probable spam. Not only will this increase the accuracy of filters (by running the retrieved content through the spam filter as well) but this would effectively be a massive distributed DOS attack on spammers. This isn't a new idea nor is it without its problems but I think it's definitely an idea whose time has come."

Comments

*ping* idea!

[Rosco P. Coltrane]

but this would effectively be a massive distributed DOS attack on spammers

Well, I never thought I'd say that one day, but when this filter comes out, I will turn into a spammer. I will send out kajillions of carefully crafted emails with lots of links to "http://enlarge.microsoft.com/", that will barely be rejected by the filter and will cause it to retrieve the content of my links to check it out, which in turn will look legit and make the email pass the filter. So I'll have achieved:

- kajillions of machine banging on M$'s machines (hell, why should I always do it myself ...)

- kajillions of users pissed at M$ for sending them spam (the filter let it pas, no?)

**EVIL MANIACAL LAUGH**