On: CryptGPT: A Simple Approach to Privacy-Preserving ...

[tripplyons]

How does this preserve privacy when everything can be decrypted?

[diwank → tripplyons]

Also to clarify- privacy preserving here means protecting from the model inference provider. Sort of like, if openai trained a GPT-4 using this scheme and gave the government the key. Then the gov can use it safely even while it’s hosted on OpenAI’s servers and OpenAI on the other hand does not need to share the model weights with the gov

[tripplyons → diwank]

Thanks for the clarification, this makes a lot more sense now!

[diwank → tripplyons]

It can only be decrypted using the encryption key. The inputs are encrypted and look like a gibberish and so are the outputs.

It preserves privacy by essentially making the inputs and outputs unreadable.