# Rethinking Benchmarks for Differentially Private Image Classification

Source: [Rethinking Benchmarks for Differentially Private Image Classification](<https://www.sota2.com/research/paper/697846b0a2b28e761d87c5ec>)

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

Data updated: 2026-01-29T05:00:05.135Z

Authors: Sabrina Mokhtari, Sara Kodeiri, Shubhankar Mohapatra, Florian Tram\\\`er, Gautam Kamath

Published: 2026-01-23T21:41:18.000Z

## Abstract

We revisit benchmarks for differentially private image classification. We suggest a comprehensive set of benchmarks, allowing researchers to evaluate techniques for differentially private machine learning in a variety of settings, including with and without additional data, in convex settings, and on a variety of qualitatively different datasets. We further test established techniques on these benchmarks in order to see which ideas remain effective in different settings. Finally, we create a publicly available leader board for the community to track progress in differentially private machine learning.

## 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/2601.17189>)

[PDF](<https://arxiv.org/pdf/2601.17189.pdf>)