News for hackers. Stuff that matters.

A comment on ImageNet contains naturally occurring Apple NeuralHash collisions. Parent comment

Re:ImageNet contains naturally occurring Apple NeuralHash co... by pbhjpbhj on Thursday August 19, 2021 @01:45PM (#28236929)
I think one of the other stories on this talked about "watermarking" in order to create a hash collision. So it need not be a non-CSAM image, a TLA could just alter an image to make it collide with a file they want to track, other countries would agree that file's hash should be in the hash list and bingo: Apple presumably provide the TLA with a list of devices holding that file.

?

[ Parent | on HN ]
Re:ImageNet contains naturally occurring Apple NeuralHash co... by duskwuff on Thursday August 19, 2021 @02:35PM (#28237517)
Except that there's a threshold involved. A single matching file doesn't trigger an investigation; it takes multiple (10+, maybe more?) matches to do that.
[ Parent | on HN ]
Re:ImageNet contains naturally occurring Apple NeuralHash co... by kemayo on Thursday August 19, 2021 @02:38PM (#28237560)
In the interview Craig Federighi gave on Friday, he said 30.[1] I have no idea if he was just throwing a number out or if that's the actual threshold.

[1]: https://tidbits.com/2021/08/13/new-csam-detection-details-em...

[ Parent | on HN ]
Re:ImageNet contains naturally occurring Apple NeuralHash co... by duskwuff on Thursday August 19, 2021 @02:57PM (#28237813)
Either way, it's high enough that adding a single file to the set wouldn't be a useful way of finding people who have that file. One attack I can imagine would be to add a whole set of closely related photos (e.g. images posted online by a known dissident) to identify the person who took them, and even that would be a stretch.
[ Parent | on HN ]