I’m not pretending to understand how homomorphic encryption works or how it fits into this system, but here’s something from the article.
With some server optimization metadata and the help of Apple’s private nearest neighbor search (PNNS), the relevant Apple server shard receives a homomorphically-encrypted embedding from the device, and performs the aforementioned encrypted computations on that data to find a landmark match from a database and return the result to the client device without providing identifying information to Apple nor its OHTTP partner Cloudflare.
That’s really cool (not the auto opt-in thing). If I understand correctly, that system looks like it offers pretty strong theoretical privacy guarantees (assuming their closed-source client software works as they say, with sending fake queries and all that for differential privacy). If the backend doesn’t work like they say, they could infer what landmark is in an image when finding the approximate minimum distance to embeddings in their DB, but with the fake queries they can’t be sure which one is real. They can’t see the actual image either way as long as the “128-bit post-quantum” encryption algorithm doesn’t have any vulnerabilies (and the closed source software works as described).
by using high-level multimodal feature descriptors, including visual similarity scores; locally stored geo-signals; popularity; and index coverage of landmarks (to debias candidate overweighting)
…and other sciencey-sounding technobabble that would make Geordi LaForge blush. Better reverse the polarity before the dilithium crystals fall out of alignment!
That’s the point. It’s a list of words that may or may not mean something and I can’t make an assessment on whether or not it’s bullshit. It’s coming from Apple, though, and it’s about privacy, which is not good for credibility.
I’m not pretending to understand how homomorphic encryption works or how it fits into this system, but here’s something from the article.
That’s really cool (not the auto opt-in thing). If I understand correctly, that system looks like it offers pretty strong theoretical privacy guarantees (assuming their closed-source client software works as they say, with sending fake queries and all that for differential privacy). If the backend doesn’t work like they say, they could infer what landmark is in an image when finding the approximate minimum distance to embeddings in their DB, but with the fake queries they can’t be sure which one is real. They can’t see the actual image either way as long as the “128-bit post-quantum” encryption algorithm doesn’t have any vulnerabilies (and the closed source software works as described).
…and other sciencey-sounding technobabble that would make Geordi LaForge blush. Better reverse the polarity before the dilithium crystals fall out of alignment!
Heh though that’s all legit right?
That’s the point. It’s a list of words that may or may not mean something and I can’t make an assessment on whether or not it’s bullshit. It’s coming from Apple, though, and it’s about privacy, which is not good for credibility.
I don’t know what a geo-signal is, but everything else listed there makes perfect sense given the context.