Hi, I am developing an iOS application that utilizes Apple’s Foundation Models to perform certain summarization tasks. I would like to understand whether user data is transferred to Private Cloud Compute (PCC) in cases where the computation cannot be performed entirely on-device.
This information is critical for our internal security and compliance reviews. I would appreciate your clarification on this matter. Thank you.
I love a question with an easy answer!
No.
Currently the Foundation Models framework only has access to the on-device model. PCC is never used. Ever. Inference is entirely on-device.
For an added layer of privacy and security assurance, Apple does not log anything about the inference other than counting that your app called the model (since it's a shared operating system resource). Apple does not log input or output, so Apple has no access to your prompts, inputs, or results.
