[Spambayes] Ideas for an MSc project please...

Skip Montanaro skip at pobox.com
Wed Feb 4 16:49:55 EST 2004

    Ryan> 1) using Bayesian-like statistics to evaluate code for virus-like
    Ryan>    behavior. I have no idea if it could work, but I would really
    Ryan>    like to see something that could stop a new worm before the
    Ryan>    anti-virus vendors have a chance to update their signatures.

SpamBayes actually already does a pretty good job of this, assuming viruses
get that far within your email infrastructure.

    Ryan> 3) A Bayesian-style web proxy filter, for libraries, schools,
    Ryan>    whatever, that evaluates web pages in real-time and blocks them
    Ryan>    if they're porn, gambling, whatever.

Start here perhaps:


and add a whole bunch of stuff that's missing: web page-specific tokenizing,
training interface, etc...


More information about the Spambayes mailing list