News for hackers. Stuff that matters.
Re:Convert Apple NeuralHash model for CSAM Detection to ONNX by misterdata on Wednesday August 18, 2021 @04:53AM (#28218975)
Re:Convert Apple NeuralHash model for CSAM Detection to ONNX by Spivak on Wednesday August 18, 2021 @03:09PM (#28225784)
While super impressive I haven't seen the thing that would actually destroy the algorithm which is given a hash and random reference image produce a new image which has that hash and looks like the reference image.
Re:Convert Apple NeuralHash model for CSAM Detection to ONNX by SV_BubbleTime on Wednesday August 18, 2021 @07:31PM (#28228519)
What you've seen is worse than that.

All you need to do to cause trouble right now, would be to get a bad image, hash it yourself, make a collision and distribute that.

Let's say for the time being that the list hashes themselves will be server-side. You won't ever get that list, but you don't need it in order to cause a collision. You would need your own supply of CSAM to hash yourself, which while distasteful is clearly also not impossible.