AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models

Jiayang Meng, Tao Huang, Hong Chen, Chen Hou, Guolong Zheng

AAAI 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Gradient inversion attacks · 1 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 gradient-guided diffusion sampling instead of fine-tuned diffusionGGSS-R vs FinetunedDiff · CelebA CNN Gaussian noise 0.01PSNR: 11.6675 -> 14.9784Improved
use gradient-guided diffusion samplingGGSS-R vs FinetunedDiff · CelebA CNN original gradientsPSNR: 29.4490 -> 41.1229Improved
increase Gaussian noise variance from 1e-4 to 1e-1 (ablation)GGSS-R · CelebA CNNPSNR: 28.0343 -> 9.0236Hurt
use Laplacian instead of Gaussian noise (ablation)GGSS-R · CelebA CNNPSNR: 24.0567 -> 24.2073 (var 1e-3)No clear effect
increase gradient batch size from 1 to 8 (ablation)GGSS-R · CelebAPSNR: 41.1229 -> 12.1425Hurt
set guidance rate to 0.20 instead of 0.01 (ablation)GGSS-R · CelebAPSNR: 26.9023 -> 41.1229Improved
raise guidance rate from 0.20 to 0.80 (ablation)GGSS-R · CelebAPSNR: 41.1229 -> 35.6101Hurt
use higher-RV attacked model (ablation)GGSS-R · CelebA, ResNet18 vs MLP-3PSNR: 10.79 -> 43.42Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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