Privately Publishable Per-instance Privacy
This work addresses privacy concerns for individuals in machine learning by providing fine-grained privacy analysis, though it is incremental as it builds on existing pDP and objective perturbation frameworks.
The paper tackles the problem of privately sharing personalized privacy losses from objective perturbation using per-instance differential privacy (pDP), proposing methods to publish these losses accurately with minimal additional privacy cost.
We consider how to privately share the personalized privacy losses incurred by objective perturbation, using per-instance differential privacy (pDP). Standard differential privacy (DP) gives us a worst-case bound that might be orders of magnitude larger than the privacy loss to a particular individual relative to a fixed dataset. The pDP framework provides a more fine-grained analysis of the privacy guarantee to a target individual, but the per-instance privacy loss itself might be a function of sensitive data. In this paper, we analyze the per-instance privacy loss of releasing a private empirical risk minimizer learned via objective perturbation, and propose a group of methods to privately and accurately publish the pDP losses at little to no additional privacy cost.