this post was submitted on 20 Oct 2023
1345 points (100.0% liked)

196

16413 readers
1135 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 9 points 1 year ago (1 children)

I'm pretty sure those AI models are trained on hashes of the material, not the material directly, so all you need to do is save a hash of the offending material in the database any time that type of material is seized

[–] [email protected] 17 points 1 year ago (2 children)

That wouldn't be ai though? That would just be looking up hashes.

[–] [email protected] 9 points 1 year ago

You're almost there...

[–] [email protected] 4 points 1 year ago (2 children)

Nah, flipping the image would completely bypass a simple hash map

From my very limited understanding it's some special hash function that's still irreversible but correlates more closely with the material in question, so an AI trained on those hashes would be able to detect similar images because they'd have similar hashes, I think

[–] [email protected] 3 points 1 year ago

Perceptual hashes, I think they're called

[–] [email protected] 2 points 1 year ago (2 children)

could you provide a source for this? that spunds very counterintuive and bad for the hash functions. especially as the whole point of AI training in this case is detecting new images. And say a small boy at the beach wearing speedos has a lot of similiarity to a naked boy. So looking by some resemblance in the hash function would require the hashes to practically be reversible.

[–] [email protected] 4 points 1 year ago* (last edited 1 year ago)

Not all hashes are for security. They're called perceptual hashes

Probably a case of definitional drift of the word, because it probably should be just for the security kind.

[–] [email protected] 3 points 1 year ago

I'm no expert, but we use those kind of hashes at my company to detect fraudulent software Here's a Wikipedia link: https://en.m.wikipedia.org/wiki/Locality-sensitive_hashing