[messaging] Modern anti-spam and E2E crypto
bascule at gmail.com
Fri Sep 5 18:58:24 PDT 2014
Open ended question:
An email provider/directory will, at least, have:
1) A sender's IP address
2) Some sort of address for routing messages to their destination
Let's augment this with:
3) An authenticated message from the destination user specifying whether a
given message is spam (and potentially, alerts for false positives if we
deliver all messages but deliver spam messages to a spam folder)
Is it possible to build an accurate model of whether or not a given message
will be spam based on these signals alone?
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Messaging