AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning

Jiaqi Wang, Roei Schuster, Ilia Shumailov, David Lie, Nicolas Papernot

NeurIPS 2022 · Federated learning and privacy › Differential privacy · approach: Private online and user-level learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase Gaussian noise scale sigma (40 to 100) in PATE (ablation)Histogram reconstruction attack · MNIST and SVHN, 10^4 queriesattack error rateImproved
low-consensus vs high-consensus histograms used as minority-group signal (consensus threshold 75%)PhD-holder detection attack · UCI Adult-Incomeprecision: 75%Improved
set sigma near 0 or very large (400) for the attacked PATE (ablation)Histogram reconstruction attack · SVHN median-consensus histogramattack error rateHurt
tighter privacy budget / higher noise (lower privacy cost)PATE defense against attack · MNIST and SVHNattack error rateNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy