# Partial sensitivity analysis in differential privacy

Source: [Partial sensitivity analysis in differential privacy](<https://www.sota2.com/research/paper/68fa6b521e209131cea2d9fe>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:11:34.522Z

Authors: Tamara T. Mueller, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Friederike Jungmann, Daniel Rueckert, Georgios Kaissis

Published: 2021-09-22T08:29:16.000Z

## Abstract

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while techniques such as individual R\\'enyi DP (RDP) allow for granular, per-person privacy accounting, few works have investigated the impact of each input feature on the individual's privacy loss. Here we extend the view of individual RDP by introducing a new concept we call partial sensitivity, which leverages symbolic automatic differentiation to determine the influence of each input feature on the gradient norm of a function. We experimentally evaluate our approach on queries over private databases, where we obtain a feature-level contribution of private attributes to the DP guarantee of individuals. Furthermore, we explore our findings in the context of neural network training on synthetic data by investigating the partial sensitivity of input pixels on an image classification task.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.10582>)

[PDF](<https://arxiv.org/pdf/2109.10582.pdf>)