4
$\begingroup$

Imagine Alice has trained a machine learning model. Bob wants to verify that whether Alice actually trained the model or not, but Alice does not want to reveal her model (because the model is personal and she wants to keep it private). So Alice wants to prove to Bob that she has the model, while not revealing any information to Bob.

Is there any zero knowledge proof to be able to do this scenario?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

I am almost two years late to this, but I think this is what you are looking for: https://dl.acm.org/doi/10.1145/3411501.3418608 (Zero-Knowledge Proofs for Machine Learning)

Improve this answer
$\endgroup$
2
  • 2
    $\begingroup$ Welcome to Cryptography We consider this as link only answer. You better provide some details of the paper... $\endgroup$
    – kelalaka
    Commented May 8, 2022 at 18:35
  • 2
    $\begingroup$ I am confident the claims in the abstract are mostly false. We can not provide proof of accuracy on a well known public dataset because it is trivial to build a model with knowledge of the test set and build a model with arbitrary accuracy and zero value. proving it has accuracy is meaningless $\endgroup$
    – Meir Maor
    Commented Jun 8, 2022 at 5:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.