The Problem with Perceptual Hashes
rentafounder.com
The Problem with Perceptual Hashes
1–10 of 440 posts
Re: The Problem with Perceptual Hashes
#2> Even at a Hamming Distance threshold of 0, that is, when both hashes are identical, I don’t see how Apple can avoid tons of collisions...
You'd want to look at the particular perceptual hash implementation. There is no reason to expect, without knowing the hash function, that you would end up with tons of collisions at distance 0.
Re: The Problem with Perceptual Hashes
#3I am fairly ignorant if this space. Do any of the standard methods use multiple hash functions vs just one?
Re: The Problem with Perceptual Hashes
#4Why wouldn't the algo check that one image has a face while the other doesn't? That would remove this particular false positive, though I'm not sure what it might cause of new ones.
Re: The Problem with Perceptual Hashes
#5I 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 post’s criticism is valid.
Re: The Problem with Perceptual Hashes
#6I do not know as much about perceptual hashing as I would like, but have considered it for a little project of my own.
Still, I know it has been floating around in the wild. I recently came across it on Discord when I attempted to push an ancient image, from the 4chan of old, to a friend, which mysteriously wouldn't send. Saved it as a PNG, no dice. This got me interested. I stripped the EXIF data off of the original JPEG. I resized it slightly. I trimmed some edges. I adjusted colors. I did a one degree rotation. Only after a reasonably complete combination of those factors would the image make it through. How interesting!
I just don't know how well this little venture of Apple's will scale, and I wonder if it won't even up being easy enough to bypass in a variety of ways. I think the tradeoff will do very little, as stated, but is probably a glorious apportunity for black-suited goons of state agencies across the globe.
We're going to find out in a big big way soon.
* The image is of the back half of a Sphynx cat atop a CRT. From the angle of the dangle, the presumably cold, man-made feline is draping his unexpectedly large testicles across the similarly man-made device to warm them, suggesting that people create problems and also their solutions, or that, in the Gibsonian sense, the street finds its own uses for things. I assume that the image was blacklisted, although I will allow for the somewhat baffling concept of a highly-specialized scrotal matching neural-net that overreached a bit or a byte on species, genus, family, and order.
Re: The Problem with Perceptual Hashes
#7Apple 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…
Re: The Problem with Perceptual Hashes
#8Apple 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.
Re: The Problem with Perceptual Hashes
#9Apple 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.
While I don’t have any inside knowledge at all, I would expect a company as big as Apple to be able to ask law enforcement to run Apple’s algorithm on data sets Apple themselves don’t have access to and report the result.
No idea if they did (or will), but I do expect it’s possible.
Re: The Problem with Perceptual Hashes
#10I'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 laughs?