Live data from Hacker News

The Problem with Perceptual Hashes

rentafounder.com

21–30 of 440 posts

Re: The Problem with Perceptual Hashes

#21

> an Apple employee will then look at your (flagged) pictures. This means that there will be people paid to look at child pornography and probably a lot of private nude pictures as well.

There are people who are paid to do that already, just generally not in corporate employment.

Re: The Problem with Perceptual Hashes

#22

> an Apple employee will then look at your (flagged) pictures. This means that there will be people paid to look at child pornography and probably a lot of private nude pictures as well.

Apple, with all those Apple == Privacy billboards plastered everywhere, is going to have a full-time staff of people with the job of looking through it's customers' private photos.

Re: The Problem with Perceptual Hashes

#24
post #5

I am not exactly buying the premise here, if you train a CNN on useful semantic categories then the representations they generate will be semantically meaningful (so the error shown in blog wouldn’t occur). I dislike the general idea of iCloud having back doors but I don’t think the criticism in this blog is entirely valid. Edit: it was pointed out apple doesn’t have semantically meaningful classifier so the blog pos…

Apple's description of the training process (https://www.apple.com/child-safety/pdf/CSAM_Detection_Techni...) sounds like they're just training it to recognize some representative perturbations, not useful semantic categories.

Re: The Problem with Perceptual Hashes

#25
post #7

Apple would not be so naive as to roll out a solution to child abuse images that has a high false positive rate. They do test things prior to release…

Test it… how exactly? This is detecting illegal material that they can’t use to test against.

They want to avoid false powitives, so you would test for that by running it over innocuous photos, anyway.

Re: The Problem with Perceptual Hashes

#26
post #18

I've also implemented perceptual hashing algorithms for use in the real world. Article is correct, there really is no way to eliminate false positives while still catching minor changes (say, resizing, cropping, or watermarking). I'm sure I'm not the only person with naked pictures of my wife. Do you really want a false positive to result in your intimate moments getting shared around some outsourced boiler room for…

> I'm sure I'm not the only person with naked pictures of my wife. I'm not completely convinced that says what you want it to.

Didn't she possibly have previous partners?

Re: The Problem with Perceptual Hashes

#27
Given all the zero day exploits on iOS I wonder if it's now going to be viable to hack someone's phone and upload child porn to their account. Apple with happily flag the photos and then, likely, get those people arrested. Now they have to, in practice, prove they were hacked which might be impossible. Will either ruin their reputation or put them in jail for a long time. Given past witch hunts it could be decades before people get exonerated.

Re: The Problem with Perceptual Hashes

#28

> an Apple employee will then look at your (flagged) pictures. Always fun when unknown strangers get to look at your potentially sensitive photos with probably no notice given to you.

They already do this for photodna-matched iCloud Photos (and Google Photos, Flickr, Imgur, etc), perceptual hashes do not change that.

Re: The Problem with Perceptual Hashes

#29

I've also implemented perceptual hashing algorithms for use in the real world. Article is correct, there really is no way to eliminate false positives while still catching minor changes (say, resizing, cropping, or watermarking). I'm sure I'm not the only person with naked pictures of my wife. Do you really want a false positive to result in your intimate moments getting shared around some outsourced boiler room for…

> Do you really want a false positive to result in your intimate moments getting shared around some outsourced boiler room for laughs?

these people also have no incentive to find you innocent for innocent photos. If they err on the side of false-negative, they might find themselves at the wrong end of a criminal search ("why didn't you catch this"), but if they false-positive they at worse ruin a random person's life.

Re: The Problem with Perceptual Hashes

#30
post #7

Apple would not be so naive as to roll out a solution to child abuse images that has a high false positive rate. They do test things prior to release…

I'm guessing you don't remember all the errors in the initial launch of Apple Maps.
Post reply on HN