Frank Solensky <fsolensky(_at_)PREMONITIA(_dot_)COM> writes:
Just posted on slashdot: a Bayesian approach to the problem that reports
to have rates of 0.5% on false positives and 0% false negative:
http://www.paulgraham.com/spam.html
The problem is that, naturally, the spammers will start running the
tool over their spam before sending it and tweaking it until it
passes. This has happened for previous techniques.
As with system security and cryptosystems, you have to assume that the
enemy knows what techniques you are using and will move to evade them.
Not, of course, that I won't add this to my armamentarium for
now. Anything to reduce the flood for as long as it will work.
--
Perry E. Metzger perry(_at_)piermont(_dot_)com
--
"Ask not what your country can force other people to do for you..."