What in that article specifically makes you not trust Thorn? They seem to me like they're trying to do good work -- preventing child exploitation -- that necessarily involves partnering with organizations whose values won't always exactly line up with theirs.
This is great, and I am going to use it in my side project. The main question I have is who has responsibility for the the 1% of CSAM not detected? Myself, as the service inadvertently hosting the material, or Thorn for not having an "accurate enough" algorithm? I suppose they just put it in their SLA terms or something.
6 comments
[ 3.4 ms ] story [ 22.6 ms ] threadRelevant: https://bohemian.ai/blog/99-accuracy-99-lie/
Sounds like it's claiming 99% precision, so 99% of positives are true positives.
Recall probably isn't great, because (a) if it were great they'd brag about it and (b) you don't get to 99% precision without sacrificing some recall.
Seems reasonable to aim high on precision, though, to avoid burying NCMEC in mis-classified data and also to avoid wrongly banning users' content.
https://projectarachnid.ca/en/