AI Paper Atlas

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

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

Hao Fang, Bin Chen, Xuan Wang, Zhi Wang, Shu-Tao Xia

ICCV 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Gradient inversion attacks · 48 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
Search intermediate feature domains after the latent space instead of latent space only (ablation)GIFD · ImageNet (BigGAN)PSNR: 13.9451 -> 18.6457Improved
Select output from the layer with least gradient matching loss instead of last searched layer (ablation)GIFD · ImageNet (BigGAN)PSNR: 18.6457 -> 19.4662Improved
Add l1 ball constraint on intermediate features (ablation)GIFD · ImageNet (BigGAN)PSNR: 19.4662 -> 20.0534Improved
Add l1 ball constraint on intermediate features (ablation)GIFD · FFHQ (StyleGAN2)PSNR: 20.5839 -> 21.3368Improved
Optimize intermediate features rather than GAN parameters (GIAS)GAN-based gradient inversion · ImageNet (BigGAN)PSNR: 17.4923 -> 20.0534Improved
Latent-only GAN search (GGL) versus GAN-free methods on ImageNetGGL · ImageNet (BigGAN)PSNR: 13.3885 vs 17.0756 (IG)Hurt
Use GIFD under Gaussian noise defense on FFHQGIFD · FFHQ, Gaussian noise std 0.1PSNR: 13.7118 vs GGL 14.8982Hurt
Use GIFD on out-of-distribution data versus GIASGIFD · ImageNet* CartoonPSNR: 19.0247 -> 22.8055Improved
Increase batch size from 1 to 32 (ablation)GIFD · ImageNetPSNR: 20.6217 -> 13.8106Hurt
Use GIFD instead of GIAS for speedGIFD · ImageNet, B=4convergence time (s): 1360.7808 -> 907.727Improved

Later papers that compared with this method

1 later accepted paper reports GIFD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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