by moderating there and then, you have delayed the removal process. what if the victim wants to ensure the photo is immediately removed on the first occurrence?
I don't know if I'm convinced it's necessary, I think just standard procedures (require account, rate limiting, bans, etc) will prevent abuse and just proving you've seen it first and delaying until moderation is good enough. But if people disagree, the problems are solvable.
-
-
i don't know enough about the false positive/negative rates of these image hashing algorithms to draw a conclusion here. "seen it first" on its own is such a fickle metric because there's an entire Internet of content that Facebook hasn't "seen" yet.
-
but it seems to me that, regardless of the pitfalls of this method, you could deploy both at once and collect at least some data on its effectiveness in practice (not comprehensive though, because people won't necessarily upload adversarial input while the old system is in place)
- 5 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.