> if it reaches step 6 it violates the privacy of the person sending
Let's say the parents are abusive, and someone wants to talk with the child about that (via chat, for some reason).
Now, if the algorithms sometimes incorrectly flag private messages that were in fact safe -- could that be mitigated by letting the sender know: "Your message will be scanned and possibly shown to the parents of the recipient" before they hit Send?
(O.t.o.h. that leaks info about the age of the recipient.)
Let's say the parents are abusive, and someone wants to talk with the child about that (via chat, for some reason).
Now, if the algorithms sometimes incorrectly flag private messages that were in fact safe -- could that be mitigated by letting the sender know: "Your message will be scanned and possibly shown to the parents of the recipient" before they hit Send?
(O.t.o.h. that leaks info about the age of the recipient.)