Privately Publishable Per-instance Privacy

• URL: http://arxiv.org/abs/2111.02281v1
• Date: Wed, 3 Nov 2021 15:17:29 GMT
• Title: Privately Publishable Per-instance Privacy
• Authors: Rachel Redberg, Yu-Xiang Wang
• Abstract summary: We consider how to privately share the personalized privacy losses incurred by objective perturbation, using per-instance differential privacy (pDP) 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.
• Score: 21.775752827149383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.