News for hackers. Stuff that matters.

A comment on Hash collision in Apple NeuralHash model. Parent comment

Re:Hash collision in Apple NeuralHash model by gorbachev on Wednesday August 18, 2021 @10:15AM (#28221196)
For individual users the risk is very small, but when you have a billion users the chances of innocent people being caught up is pretty much 100%.

Platform owners like Google, Apple, Twitter and Facebook should really keep stuff like that in mind when they deploy algorithmic solutions like this.

Like dhosek said, the manual review step should reduce the risk quite a bit, though.

[ Parent | on HN ]
Re:Hash collision in Apple NeuralHash model by Grustaf on Wednesday August 18, 2021 @10:28AM (#28221404)
They did keep it in mind, that's why they require 30 matches, which gets the false positive rate down to 1 in a trillion per year, so on average it will happen about 1 per millennium, given a billion users.

So that's per photo library, not per photo. The rate per photo in their testing was 3 in 100 million, then they added a 30x safety margin and assumed it's actually 1 in a million.

https://www.zdnet.com/article/apple-to-tune-csam-system-to-k...

[ Parent | on HN ]