Per-instance Differential Privacy

We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard DP and inherits all its desirable properties, e.g., composition, invariance to side information and closedness to postprocessing, except that they all hold for every instance separately. When the data is drawn from a distribution, we show that per-instance DP implies generalization. Moreover, we provide explicit calculations of the per-instance DP for the output perturbation on a class of smooth learning problems. The result reveals an interesting and intuitive fact that an individual has stronger privacy if he/she has small "leverage score" with respect to the data set and if he/she can be predicted more accurately using the leave-one-out data set. Our simulation shows several orders-of-magnitude more favorable privacy and utility trade-off when we consider the privacy of only the users in the data set. In a case study on differentially private linear regression, provide a novel analysis of the One-Posterior-Sample (OPS) estimator and show that when the data set is well-conditioned it provides $(\epsilon,\delta)$-pDP for any target individuals and matches the exact lower bound up to a $1+\tilde{O}(n^{-1}\epsilon^{-2})$ multiplicative factor. We also demonstrate how we can use a "pDP to DP conversion" step to design AdaOPS which uses adaptive regularization to achieve the same results with $(\epsilon,\delta)$-DP.