Saved in:
Bibliographic Details
Main Authors: Mokhtari, Sabrina, Kodeiri, Sara, Mohapatra, Shubhankar, Tramèr, Florian, Kamath, Gautam
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17189
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912851289964544
author Mokhtari, Sabrina
Kodeiri, Sara
Mohapatra, Shubhankar
Tramèr, Florian
Kamath, Gautam
author_facet Mokhtari, Sabrina
Kodeiri, Sara
Mohapatra, Shubhankar
Tramèr, Florian
Kamath, Gautam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17189
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rethinking Benchmarks for Differentially Private Image Classification
Mokhtari, Sabrina
Kodeiri, Sara
Mohapatra, Shubhankar
Tramèr, Florian
Kamath, Gautam
Machine Learning
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.
title Rethinking Benchmarks for Differentially Private Image Classification
topic Machine Learning
url https://arxiv.org/abs/2601.17189