Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ImageNet contains naturally occurring Apple NeuralHash collisions

blog.roboflow.com

Post reply on HN
Print view View original

461–470 of 530 posts

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#461

Post by yeldarb »

solidgol wrote: post #438
dang wrote: post #413

Earlier quoted context omitted.

What would be a better (i.e. more accurate and neutral) title?

A reply by the moderator! I am honored. I think the headline should be: ImageNet contains about as many naturally occurring NeuralHash collisions as Apple predicts

Hey, OP here - while that is also true, I think the average observer would think this number _should_ be zero. The fact that any exist at all is surprising (but the fact that only two exist is also surprising; I expected to find either zero or lots when I started the script).

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#462

Post by nonbirithm »

short_sells_poo wrote: post #327
nonbirithm wrote: post #118

Earlier quoted context omitted.

And it's fine to treat everyone as a potential criminal when we entrust our data on the same company's servers? No matter if on-device scanning makes surveillance easier than ever, the surveillance itself was still a significant possibility up to this point with server-side scanning. Imagine how many petabytes of user data already exist in the cloud.

So in your mind because bad thing X is already happening, it's completely OK for bad thing XY to also start happening?

No, it's that in spite of there already being an invasive scanning process in place for this long at every major tech company that handles user data, nobody seemed to care until now.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#463

Post by fortran77 »

stefan_ wrote: post #282
nomel wrote: post #216

Earlier quoted context omitted.

Why is this question being downvoted? I too would like to know what this attack achieves. From what I see, the end result of false flagging is either someone has CSAM in iCloud and you push them over the threshold that results in reporting and prosecution, or there is no CASM, so the reviewer sees all of the hash collision images, including those that are natural. Is the problem that an attacker can force natural has…

You are one underpaid random guy in India looking at CSAM all day clicking the wrong button away from a raid of your home and the end of your life as you know it.

Yes. Once you're accused, your life is over. Nobody will pay any attention to a news article the next week saying they found nothing.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#464

Post by yunesj »

endisneigh wrote: post #8

It doesn’t matter if there are collisions if the two images don’t actually look the same. Do people honestly believe a single CSAM flag from an “innocent” image is going to result in someone going to prison in America? PhotoDNA has existed for over a decade doing the same thing with no instances that I have heard of. If some corrupt government wants to get you they don’t need this. They can just unilaterally say you’…

You ask for examples a few times. Here’s one. Computers confiscated from a liberty activist and his radio station. No CP-related charges pressed in the 5 years since they confiscated his computers.

I’m guessing most times this happens, the accused try to keep it on the DL.

https://www.wmur.com/article/fbi-raids-radio-talk-show-host-...

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#466

Post by ec109685 »

csmpltn wrote: post #242
mrtranscendence wrote: post #179

Earlier quoted context omitted.

Why would anyone bother with such an attack? The end result is that some peon at Apple has to look at the images and mark them as not CSAM. You've cost someone a bit of privacy, but that's it.

> "The end result is that some peon at Apple has to look at the images and mark them as not CSAM. You've cost someone a bit of privacy, but that's it." This can be abused to spam Apple's manual review process, grinding it down to a halt. You've cost Apple time and money by making them review each such fake report.

It can’t be. There’s a different private hash function that also has to match that particular csam image’s hash value before a human sees it. An adversarial attack can’t produce that one since the expected value isn’t known.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#467

Post by ec109685 »

saithound wrote: post #232
mrtranscendence wrote: post #179

Earlier quoted context omitted.

Why would anyone bother with such an attack? The end result is that some peon at Apple has to look at the images and mark them as not CSAM. You've cost someone a bit of privacy, but that's it.

Okay, let's play peon. Here are three perfectly legal and work-safe thumbnails of a famous singer: https://imgur.com/a/j40fMex . The singer is underage in precisely one of the three photos. Can you decide which one? If your account has a large number of safety vouchers that trigger a CSAM match, then Apple will gather enough fragments to reassemble a secret key X (unique to your device) which they can use to decrypt…

None of those thumbnails (or visual derivatives) will match the hash value of the known csam you are trying to simulate since it won’t be possible to know the hash value target since that hash function is private.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#468

Post by ec109685 »

saithound wrote: post #343
ChrisKnott wrote: post #311

Earlier quoted context omitted.

Can you explain how these theoretical political memes hash-match to an image in the NCMEC database, and then also pass the visual check? > "No, this misses the point completely. You cannot easily trigger any automated systems merely by taking photos of 17.9 year olds and sending them to people." Did I say "taking"? I am talking about sending (theoretical) actual images from the NCMEC database. This is functionally id…

Yes, I can. This is just one possible strategy: there are many others, where different things are done, and where things are done in a different order. You use the collider [1] and one of the many scaling attacks ([2] [3] [4], just the ones linked in this thread) to create an image that matches the hash of a reasonably fresh CSAM image currently circulating on the Internet, and resizes to some legal sexual or violent…

This attack doesn’t work. If the resized image doesn’t match the CSAM image your NeuralHash mimicked, then when Apple runs it’s private perceptual hash, the hash value won’t match the expected value and it will be ignored without any human looking at it.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#469

Post by joe_the_user »

endisneigh wrote: post #8

It doesn’t matter if there are collisions if the two images don’t actually look the same. Do people honestly believe a single CSAM flag from an “innocent” image is going to result in someone going to prison in America? PhotoDNA has existed for over a decade doing the same thing with no instances that I have heard of. If some corrupt government wants to get you they don’t need this. They can just unilaterally say you’…

It doesn’t matter if there are collisions if the two images don’t actually look the same. Do people honestly believe a single CSAM flag from an “innocent” image is going to result in someone going to prison in America?

I understand that the system as stated today has multiple safeguards against such things happening but...

Given the sum-total of bs I've seen happening in this country, yes, believe that kind of thing is quite possible.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#470

Post by drdeca »

bsenftner wrote: post #378
tshaddox wrote: post #371

Earlier quoted context omitted.

Well, no, I don't think they have any way of force install updates, but that would also apply to this update to add CSAM hashing.

If your wifi is enabled and the phone is attached to power, apple updates without any request. I've been trying not to update my iPhone, but recently I left the wifi on when charging and it updated.

Do you think this changed since 14.0.1 (which is from Sept 10 2020)? Mine is still on 14.0.1 , and I leave it plugged in with wifi every night.
Post reply on HN