AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Privacy Auditing with One (1) Training Run

Thomas Steinke, Milad Nasr, Matthew Jagielski

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 7 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 number of auditing examples m (ablation)one-run audit · white-box CIFAR-10epsilon lower boundImproved
add more non-auditing training examples (n-m) (ablation)one-run audit · white-box CIFAR-10epsilon lower boundNo clear effect
increase number of DP-SGD iterations at equal privacy (ablation)one-run audit · white-box CIFAR-10epsilon lower boundNo clear effect
increase number of auditing examples m (ablation)one-run audit · black-box input-spaceepsilon lower boundMixed
add superfluous training data (ablation)one-run audit · black-box input-spaceepsilon lower boundHurt
insert auditing canaries in DP-SGD trainingDP-SGD · CIFAR-10 epsilon=8test accuracy: 78 -> 76Hurt
increase number of guesses r in idealized randomized response (ablation)one-run audit · idealized epsilon=4epsilon lower boundImproved
increase number of guesses r in idealized Gaussian setting (ablation)one-run audit · idealized Gaussianepsilon lower boundHurt

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