8 comments

  • LoganDark a few seconds ago

    One flaw with homomorphic encryption is that it only guarantees that you don't see the inputs or outputs of the computation without the key, but it doesn't guarantee that the computation is the one you want. For example, the computation could be adversarial for certain inputs.

  • noident 15 minutes ago

    Does this rely on the Trust Me Bro model, or is there some way for the client to verify that the provider actually isn't able to see your inputs?

    I want to read a whitepaper but all I can find is the tl;dw conference presentation

      eslaught 7 minutes ago

      The linked project page [1] claims to be fully homomorphic. Assuming the claim holds (I haven't verified it), then there is provably no way for Google or anyone else to obtain any information from the encrypted data or computation performed on them.

      FHE is traditionally horrifically slow, so it's hard to imagine running anything beyond toy models with it. They list some applications on the original article page, but (presumably) they must be dramatically stripped down in order to run within any reasonable time budget. This is not going to run anything like a Sol/Opus any time soon.

      [1]: https://heir.dev/

  • FloatArtifact an hour ago

    Encryption or not, if it's on somebody else's server, it isn't yours. I don't believe Google has my best interest.

      u1hcw9nx an hour ago

      With Fully Homomorphic Encryption it's nobody elses.

      The basic idea of of the project is to remove the need for trust.

        unsungNovelty 20 minutes ago

        It's google. They are good at engineering. Not at creating trust. After the bizillionth time they have broken trust, there is no need for benefit of the doubt.

        thih9 11 minutes ago

        To what end?

      krunck 16 minutes ago

      It's FHE for "cryptographically-secure private AI inference" not for every other service where they snoop into your behavioral information.