I add differential privacy (DP) to my machine learning models by using PyTorch-DP. PyTorch-DP supplies me with the values: εand δ. I know that the εtells us something about the probability ρ that the privacy of individuals in the dataset (DP) is broken. So, a ρ of 0.5 might correspond to an ε of 2 (depending on the statistics that are released). So now, my question is: with the implementation that PyTorch-DP uses (Renyi DP calculated by using the Moments Accountant method), to what ρ does the ε correspond to? If I do not know this, how can I say something "meaningful" about the level of privacy ρ that ε satisfies?

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.