Taking a picture instantly after would probably create a different hash value. The thing about hashing is that even if one bit is different between source images, the resulting hashes would look entirely different.

I suppose I could conceive of a proprietary hash algorithm that would allow for fuzzy matching of iris photos, but as you said, eyes taken years apart in different conditions wouldn't match the original hash. Or falsely match similar looking eyes. It's not like this system allows them to get high resolution perfectly lit iris photos, after all.

The whole thing sounds dubious, and I suspect AI is mentioned solely to secure investor funding, much like how several years back everything mentioned Blockchain.

[–] UFODivebomb@programming.dev 1 points 1 year ago

They are likely using a form of https://en.wikipedia.org/wiki/Perceptual_hashing

The noise level a perceptual hash is sensitive to can be tuned.

The "falsely match similar looking" is harder than one would expect. I used to work on an audio fingerprinting system which was extremely robust to "similar" audio matching. What sounded similar to us was always identified uniquely by the hash with high confidence.

For example. Take the same piano piece done by the same artists on the same piano performed as close as they could to the same: never confused the perceptual hash with ~10 sec of audio. Not once. We could even identify how much of a pre-recorded song was used in a "live" performance.

There are adversarial attacks for perceptual hashes. However, "similar eyes" would not be one to a standard perceptual hash. More like: a picture of an abstract puppy happens to have the same hash as an eye.

I'd be curious on the details of the hash. That is necessary to know what the adversely attacks are. But I see no mention of the details. Which is suspicious on it's own.