Papers › GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

9 Aug 2023ICCV 2023 1arXiv:2308.04699archive 2025-07-28

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

Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server. Recent studies find that the exchanged gradients also take the risk of privacy leakage, e.g., an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. However, performing gradient inversion attacks in the latent space of the GAN model limits their expression ability and generalizability. To tackle these challenges, we propose Gradient Inversion over Feature Domains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers. Instead of optimizing only over the initial latent code, we progressively change the optimized layer, from the initial latent space to intermediate layers closer to the output images. In addition, we design a regularizer to avoid unreal image generation by adding a small l₁ ball constraint to the searching range. We also extend GIFD to the out-of-distribution (OOD) setting, which weakens the assumption that the training sets of GANs and FL tasks obey the same data distribution. Extensive experiments demonstrate that our method can achieve pixel-level reconstruction and is superior to the existing methods. Notably, GIFD also shows great generalizability under different defense strategy settings and batch sizes.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ffhibnese/gifd officialmentioned in paperpytorchMITSyntology: 13 samples, 12 ran (3 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
9ran
1unverified

Licence: 1 of the 13 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ffhibnese/gifd. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ffhibnese/gifd official repository 13 samples, 12 ran (3 instrument-failed) · 1 unverified
activation_errors in 6 papers inversefed/metrics.py ran · our draft was wrong MIT (permissive) · e551d62ffffcfda9 · report fixture: signature model:callable/0/?, x1:Tensor/2/float, x2:Tensor/2/float · returned defaultdict · level recorded 2026-09-25
additive_noise defense.py ran MIT (permissive) · 1770bad65e763b78 · report fixture: signature input_gradient:list/1/Tensor, std:float/0/float · returned list · level recorded 2026-09-24
densenet_cifar in 6 papers inversefed/nn/densenet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 7db01b64f42f28ee · report fixture: signature num_classes:int/0/int · returned _DenseNet · level recorded 2026-09-24
gradient_clipping in 6 papers defense.py ran MIT (permissive) · 49e3def5d3ba54c9 · report fixture: signature input_gradient:list/1/Tensor, bound:int/0/int · returned list · level recorded 2026-09-24
gradient_compression defense.py ran MIT (permissive) · aae188414ae38f51 · report fixture: signature input_gradient:list/1/Tensor, percentage:int/0/int · returned list · level recorded 2026-09-24
load_config in 389 papers rec_mult.py ran MIT (permissive) · 21cecdf2721c9a12 · report fixture: signature config_path:str/0/str · returned dict · level recorded 2026-09-24
merge in 85 papers inversefed/nn/revnet_utils.py ran fingerprinted MIT (permissive) · 2d15f050207aff53 · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
inversefed/metrics.py ran MIT (permissive) · 5ef2f520281c0bdf · report fixture: signature img_batch:Tensor/4/float, ref_batch:Tensor/4/float, batched:bool/0/bool, factor:float/0/float · returned float · level recorded 2026-09-25
reconstruction_costs in 8 papers inversefed/reconstruction_algorithms.py ran MIT (permissive) · 24dd50ff238a3c31 · report fixture: signature gradients:list/1/list, input_gradient:list/1/Tensor, cost_fn:str/0/str, indices:str/0/str, weights:str/0/str · returned Tensor · level recorded 2026-09-24
split in 67 papers inversefed/nn/revnet_utils.py ran fingerprinted MIT (permissive) · 781553d9de1bec97 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
total_variation in 14 papers inversefed/metrics.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 3d23162c75564e01 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-25
training_strategy inversefed/optimization_strategy.py ran MIT (permissive) · add5009f628a413f · report fixture: signature strategy:str/0/str, lr:float/0/float, epochs:int/0/int, dryrun:bool/0/bool · returned ConservativeStrategy · level recorded 2026-09-24
construct_model in 11 papers inversefed/nn/models.py unverified MIT (permissive) · 1e0ee02f7f2be4e0 · report

Tasks

Federated LearningImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections