AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Efficient Public Verification of Private ML via Regularization

Zoë Ruha Bell, Anvith Thudi, Olive Franzese, Nicolas Papernot, Shafi Goldwasser

ICML 2026 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 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
Run verification over a LAN instead of locally (ablation)Phased ERM certification · MNIST full verificationtime (hr): 5.54 -> 5.73Hurt
Run verification over a WAN (200 Mb) instead of locally (ablation)Phased ERM certification · MNIST full verificationtime (hr): 5.54 -> 6.70Hurt
Run verification over a WAN (100 Mb) instead of locally (ablation)Phased ERM certification · MNIST full verificationtime (hr): 5.54 -> 6.88Hurt
Replace prior DP-SGD certification with modified phased ERM certificationMNIST logistic regression DP verification · MNISTverification time (hr): 100 -> 3Improved
Replace DP-SGD gradient checks with phased ERM gradient checksMNIST DP certification · MNISTgradients verified: 255,280 -> 60,000Improved
Vary epsilon from 1.665 to 0.166 (ablation)Phased ERM certification · MNIST full verificationtime (hr): 3.10 -> 3.19No clear effect
Increase noise sigma from 0.1 to 10 (ablation)Gaussian commitment · Noise generationtime (ms/sample): 0.071 -> 0.94Hurt
Increase features from 512 to 2048 (ablation)Gradient verification · Gradient verificationtime (ms/gradient): 109 -> 432Hurt
Require small gradient norm and divide delta across phases in phased ERMPhased ERM · MNIST logistic regression trainingtraining time (s): 14.37 -> 19.24Mixed

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