2
$\begingroup$

I add differential privacy (DP) to my machine learning models by using PyTorch-DP. PyTorch-DP supplies me with the values: $\epsilon$ and $\delta $. I know that the $\epsilon$ tells us something about the probability $\rho$ that the privacy of individuals in the dataset (DP) is broken. So, a $\rho$ of 0.5 might correspond to an $\epsilon$ 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 $\rho$ does the $\epsilon$ correspond to? If I do not know this, how can I say something "meaningful" about the level of privacy $\rho$ that $\epsilon$ satisfies?

$\endgroup$
2
  • $\begingroup$ This is cross-posted on Information Security site. Please if you are the same person, delete one copy. $\endgroup$
    – kelalaka
    Jun 24 '20 at 14:25
  • $\begingroup$ I don't think your interpretation of $\varepsilon$ is quite right. What do you mean by "the probability $\rho$ that the privacy of individuals in the dataset is broken"? I generally find the Bayesian interpretation of $\varepsilon$ to be the most accessible. I also don't understand how this question is about Rényi privacy, whose parameters are not $(\varepsilon,\delta)$ but $(\alpha,\varepsilon)$. Can you clarify? $\endgroup$
    – Ted
    Sep 25 '20 at 12:17
1
$\begingroup$

I don't think your interpretation of $\varepsilon$ in DP is correct. You can find a decent explanation of this parameter in this crypto.SE question and links therein.

The best intuition I have for Rényi privacy is that it bounds the average of the privacy loss) $L(O)$: instead of being a worst-case property, like DP ("for all outputs $O$, $L(O)$ is lower than $\varepsilon$"), Rényi privacy is an average-case property ("when we average $L(O)$ across all possible outputs $O$, the result is lower than $\varepsilon$"). The $\alpha$ parameter determines which kind of average we're using: used: $\alpha=1$ bounds the arithmetic mean of $L(O)$, $\alpha=2$ bounds the arithmetic mean of $e^{L(O)}$, $\alpha=3$ bounds the quadratic mean of $e^L(O)$, etc.

$\endgroup$

Your Answer

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

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