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

121–130 of 530 posts

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#121

Post by dgellow »

breuleux wrote: post #67
stickfigure wrote: post #19

> it's not obvious how we can trust that a rogue actor (like a foreign government) couldn't add non-CSAM hashes to the list to root out human rights advocates or political rivals. Apple has tried to mitigate this by requiring two countries to agree to add a file to the list, but the process for this seems opaque and ripe for abuse. If the CCP says "put these hashes in your database or we will halt all iPhone sales in…

Presumably Apple would be afraid that, say, the EU becomes suspicious, issues a court order to obtain the hashes, notices they cannot audit the CCP hashes, pointedly asks "what is this", becomes absolutely livid that their citizens are spied on by a country that is not them, fines Apple out the wazoo, then extradites whoever is responsible and puts them in prison. I mean, China's not the only player in this. Putting…

I think that you overestimate the EU reaction. Every few years we learn that our Europeans leaders and some citizens have been again spied by foreign powers, such as the US, and absolutely nothing ever happened.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#122

Post by stjohnswarts »

axelf4 wrote: post #116
yongjik wrote: post #110

Earlier quoted context omitted.

These scenarios sound rather like "the wrong side of airlock" stories[1]. Why would China go through an elaborate scheme with fake child-porn hashes, when it can already arrest these people on made-up charges, and simply tell Apple to provide the private key for their phones, so that they can read and insert whatever real/fake evidences they want? [1] I'm stealing the expression from this excellent article: https://d…

That is not a good comparison. The extra hashes would help China find out about more borderline citizens than it otherwise would have.

Have we established that a US NGO is accepting "CSAM" hashes from China or that they are cooperating with them at all? That seems unlikely and Apple hasn't yet announced plans with how they're going to scan phones in China, I mean wouldn't China just demand outright to have full scanning capabilities of anything on the phone since you don't have any protection at all from that in China?

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#123

Post by throwaway287391 »

sweezyjeezy wrote: post #81
matsemann wrote: post #5

> By taking advantage of the birthday paradox, and a collision search algorithm that let me search in n(log n) time instead of the naive n^2 Someone got more details on that? How does the birthday paradox come into play here?

He means that even though the chance of two random images colliding is ~ 1/ 2 trillion, once you get up to a set of order sqrt(2 trillion) you have a good chance of having a collision amongst all pairs.

That explains the "birthday paradox" part, what I'm unclear on is the need for a "collision search algorithm" that isn't just "build a hashmap" which should take roughly O(N) time. (I suppose it could just be that, but I'm surprised it's even mentioned in that case. In my uncle(?) comment I wrote an 8 line Python implementation that runs in 3 seconds on my laptop.)

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#125

Post by nanis »

yeldarb wrote: post #104
nanis wrote: post #84

It sounds like there is code that enables anyone to compute the perceptual hash for an image. Is this code published somewhere?

The instructions are here: https://github.com/AsuharietYgvar/AppleNeuralHash2ONNX This was discussed on HN yesterday here (and a few other front-page stories): https://news.ycombinator.com/item?id=28218391

Got it ... Here's the part I was missing:

> You will need 4 files from a recent macOS or iOS build:

    neuralhash_128x96_seed1.dat
    NeuralHashv3b-current.espresso.net
    NeuralHashv3b-current.espresso.shape
    NeuralHashv3b-current.espresso.weights
So, for clarity, Apple did not publish the model/code for others to be able to use/test etc. Someone found a clever way to convert the stored model into an open format and therefore others with access to those files are able to experiment.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#126

Post by hyperbovine »

Err, most of these are not naturally occurring pairs since in each case the images differ by a human manipulation (resolution reduction, drawing an arrow, changing the watermark, changing the aspect ratio)---which I'm guessing is viewed as a feature not a bug by the designers of this system. The axe and the nematode comes closest, and even then, they are low-res and visually similar. What would be far more concerning is a hash collision between a picture of a piano and a picture of an elephant, but nothing like that is happening here.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#127

Post by stjohnswarts »

slg wrote: post #113
colpabar wrote: post #101

Earlier quoted context omitted.

> It is only moving from the cloud to the local device. But isn't that exactly why this is such a big deal? It sets a precedent that it's ok that devices are scanning your local device for digital contraband. Sure, right now it's only for photos that are going to be uploaded to iCloud anyway. But how long before it scans everything, and there's no way to opt out? I don't see this as so much a question of apple's trus…

>But how long before it scans everything, and there's no way to opt out? Do we think this is detectable? If yes, then why worry about it if we will know when this switch is made? If not, why did we trust Apple that this wasn't happening already? That is the primary thing I don't understand, this fear rests on an assumption that Apple is a combination of both honest and corrupted. If they are honest, we have no reason…

You're viewing trust in apple as a binary choice. It is not. Trust is a spectrum like most things. You need to get away from that digital thinking. It's the whole reason we have to challenge government and be suspicious of it. It's the same with companies.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#128

Post by vhold »

> By taking advantage of the birthday paradox, and a collision search algorithm that let me search in n(log n) time instead of the naive n^2, I was able to compare the NeuralHashes of over 2 trillion image pairs in just a few hours.

I think you could just do "sort | uniq -c | sort -nr" on the neuralhash values to find the most frequently occurring ones pretty fast?

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#129

Post by stickfigure »

yongjik wrote: post #110
stickfigure wrote: post #19

> it's not obvious how we can trust that a rogue actor (like a foreign government) couldn't add non-CSAM hashes to the list to root out human rights advocates or political rivals. Apple has tried to mitigate this by requiring two countries to agree to add a file to the list, but the process for this seems opaque and ripe for abuse. If the CCP says "put these hashes in your database or we will halt all iPhone sales in…

These scenarios sound rather like "the wrong side of airlock" stories[1]. Why would China go through an elaborate scheme with fake child-porn hashes, when it can already arrest these people on made-up charges, and simply tell Apple to provide the private key for their phones, so that they can read and insert whatever real/fake evidences they want? [1] I'm stealing the expression from this excellent article: https://d…

Who said anything about fake porn hashes? China can just say to Apple: We want everyone whose phones contain XYZ subversive content.

Don't like it? Don't sell phones. Apple will cave.

Note that you don't even have to arrest everyone. The fear is enough to prevent thoughtcrime.

Re: ImageNet contains naturally occurring Apple NeuralHash collisions

#130

Post by nonbirithm »

foerbert wrote: post #79
shuckles wrote: post #36

Earlier quoted context omitted.

That is literally the status quo with every cloud service. Apple, unlike the others, has said that they will evaluate you on the basis of what’s included in the associated data of your safety voucher, and you can inspect those contents because they’re shipped in the client. Facebook, for all I know, might be calculating a child predator likelihood score on my account based on how often I look up my middle school ex-g…

I don't think we can just appeal to the status quo here and assume it's acceptable. There's a couple reasons. First, how many people really understood this previously? Did society at large actually knowingly accept the current state of things, or did it just happen without most people realizing it? Even here on HN where we'd expect to find people way more knowledgeable about it than in general I'm not sure how well k…

If the problem is a lack of understanding of the status quo, then it isn't fair to criticize Apple alone. People ought to demand answers about the state of server-side scanning from Facebook and Microsoft and everyone else that employs PhotoDNA as well. The most popular article submitted to HN with "PhotoDNA" in the title garnered hardly any interest at all, even though someone there implied that a hash collision might be possible five years in advance.

https://news.ycombinator.com/item?id=11636502

Post reply on HN