AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Personalized Federated Training of Diffusion Models with Privacy Guarantees

Kumar Kshitij Patel, Bingqing Jiang, A F M Mahfuzul Kabir, Weitong Zhang, Difan Zou, Lingxiao Wang

CVPR 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private federated learning · 2 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
use PFDM (shared noisy-data model + personalized local model) instead of non-collaborative trainingPFDM · CelebAFID (minority): 41.38 -> 28.09Improved
use PFDM instead of non-collaborative trainingPFDM · CIFAR-10FID (minority): 36.44 -> 35.78No clear effect
use PFDM instead of non-collaborative trainingPFDM · Colorized MNISTFID (avg): 4.09 -> 3.26Improved
use PFDM instead of non-private federated trainingPFDM · CelebAFID (avg): 13.15 -> 23.10Hurt
use PFDM instead of federated DPDMPFDM · MNISTFID (avg): 33.73 -> 6.96Improved
increase number of clients from 4 to 128 with fixed total data (ablation)PFDM · CIFAR-10FIDImproved
train global model on noisy clipped data with DP guaranteePFDM global model · CIFAR-10 membership inferenceAUC: 82.13 -> 50.01Improved
use PFDM global model for reconstruction attack vs no attackPFDM · CelebARecovery score: 1.13 -> 1.12No 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