Ronan Cunniffe wrote:
>> On Wed, 14 Apr 2004, Bryan O'Donoghue wrote:
>>>>Ronan Cunniffe wrote:
>>>>hmmm, this guy claims a Bayesian algorithm will hit 995 spams per thousand,
>>with zero false positives.
>>> I could claim that too...
>> Bayesian filters aren't magic, they're a piece of (mathematical)
> engineering, and have precise and calculable modes of failure. The
> spammers have calculated and precisely targetted one of them.
>> Bayesian filters use past patterns as templates to judge which of N bins
> a new e-mail matches, and by adding the new e-mail to the relevant bin,
> can increase the resolution of the template patterns.
It's a neat idea though, using a template to teach the machine to recognise spam.
> You simply can't do this if the messages are perfectly random (this being
> one of the practical tests of randomness).
True, any system or quasi intelligent entity might not cope well with the
unknown. A human can use intuition, which is in itself a sort of pseudo random
behaviour.
What I find interesting, is the lack of false positives. If for example I
included the word sex, or sexy enough in an email would an advanced Bayesian
filter which was aware of my email address decide, that the email was spam and
if not, what if the email had been spoofed?
I suppose it's interesting from the stand point of writing software that acts
in an intelligent manner, but, more then just being a neat algorithm to munge
text, learns.
I guess if such an algorithm generated sufficient heat, we could call it alive.
> What you can do is force the
> spammers out the main body and into an attachment. Whether this is
> progress, I don't know.
I'd say that's certainly progress.
Enter Godel's incompletness theorem. The machine can't stop spam it sends to
itself.
Ha ha!
--
Bryan O'Donoghue
Embedded Software Engineer
Europlex Technologies Ltd
Clonshaugh Business & Technology Park
Dublin 17
Ireland
T:+353 (0) 1 2500500
F:+353 (0) 1 2500590
E:bryano at euoplex.ie
W:www.europlex.ie
Maintained by the ILUG website team. The aim of Linux.ie is to
support and help commercial and private users of Linux in Ireland. You can
display ILUG news in your own webpages, read backend
information to find out how. Networking services kindly provided by HEAnet, server kindly donated by
Dell. Linux is a trademark of Linus Torvalds,
used with permission. No penguins were harmed in the production or maintenance
of this highly praised website. Looking for the
Indian Linux Users' Group? Try here. If you've read all this and aren't a lawyer: you should be!
