Re:Hash collision in Apple NeuralHash model
by kleene_op on Wednesday August 18, 2021 @09:07AM
(#28220485)
Not necessarily.
If you know the method used by Apple to scale down flagged images before they are sent for review, you can make it so the scaled down version of the image shows a different, potentially misleading one instead:
If you know the method used by Apple to scale down flagged images before they are sent for review, you can make it so the scaled down version of the image shows a different, potentially misleading one instead:
https://thume.ca/projects/2012/11/14/magic-png-files/
At the end of the day:
- You can trick the user into saving an innocent looking image
- You can trick Apple NN hashing function with a purposely generated hash
- You can trick the reviewer with an explicit thumbnail
There is no limit to how devilish one can be.