# Privately Publishable Per-instance Privacy

arXiv: https://arxiv.org/abs/2111.02281 · HTML: https://mlsanity.com/paper/2111.02281/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 3 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [Scalable Private Learning with PATE](https://mlsanity.com/paper/1802.08908/) (2018)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [Large Scale Private Learning via Low-rank Reparametrization](https://mlsanity.com/paper/2106.09352/) (2021)
- [Individual Privacy Accounting via a Renyi Filter](https://mlsanity.com/paper/2008.11193/) (2020)
- [Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12](https://mlsanity.com/paper/1709.02753/) (2017)
- [Private Matchings and Allocations](https://mlsanity.com/paper/1311.2828/) (2013)
- [Fast Differentially Private Matrix Factorization](https://mlsanity.com/paper/1505.01419/) (2015)
- [Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM](https://mlsanity.com/paper/1705.10829/) (2017)

## Built on by (most cited first, 12 of 12)

- [Bounding Training Data Reconstruction in DP-SGD](https://mlsanity.com/paper/2302.07225/) (2023)
- [Offline Reinforcement Learning with Differential Privacy](https://mlsanity.com/paper/2206.00810/) (2022)
- [Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent](https://mlsanity.com/paper/2206.02617/) (2022)
- [Individual Privacy Accounting with Gaussian Differential Privacy](https://mlsanity.com/paper/2209.15596/) (2022)
- [Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners](https://mlsanity.com/paper/2401.00583/) (2023)
- [Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy](https://mlsanity.com/paper/2301.00301/) (2022)
- [Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models](https://mlsanity.com/paper/2410.03026/) (2024)
- [Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile](https://mlsanity.com/paper/2306.15790/) (2023)
- [On the Privacy of Selection Mechanisms with Gaussian Noise](https://mlsanity.com/paper/2402.06137/) (2024)
- [Privacy Amplification for the Gaussian Mechanism via Bounded Support](https://mlsanity.com/paper/2403.05598/) (2024)
- [Quadratic Objective Perturbation: Curvature-Based Differential Privacy](https://mlsanity.com/paper/2605.05905/) (2026)
- [Towards Optimal Differentially Private Regret Bounds in Linear MDPs](https://mlsanity.com/paper/2504.09339/) (2025)

## Abstract (arXiv)

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.