On Fri, 30 Sep 2011 10:07:16 -0700 Adam Katz <antis...@khopis.com> wrote:
> Right, phish thrives on low volume so it can stay under the radar. > Bayes is not good at catching such things. We catch many phishing attempts using Bayes. However, our Bayes corpus is rather large... about 770,000 spam and 909,000 ham messages collected over a window of 21 days. > > If we could organise a working group or something, and/or collect > > some examples, I'd happily help with writing some rules > > specifically for these. > I'd be game for helping there too. Phish Tank is a starting point, > though it is riddled with non-phish (both spam and FPs). APER is also fairly useful: http://code.google.com/p/anti-phishing-email-reply/ It lists known phishing reply addresses and URLs. (It's reactive, though, so like a virus scanner, it can only protect against threats someone has already reported.) Regards, David.
