Papers › GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

9 Sep 2019arXiv:1909.03935archive 2025-07-28

Dingfan Chen, Ning Yu, Yang Zhang, Mario Fritz

Deep learning has achieved overwhelming success, spanning from discriminative models to generative models. In particular, deep generative models have facilitated a new level of performance in a myriad of areas, ranging from media manipulation to sanitized dataset generation. Despite the great success, the potential risks of privacy breach caused by generative models have not been analyzed systematically. In this paper, we focus on membership inference attack against deep generative models that reveals information about the training data used for victim models. Specifically, we present the first taxonomy of membership inference attacks, encompassing not only existing attacks but also our novel ones. In addition, we propose the first generic attack model that can be instantiated in a large range of settings and is applicable to various kinds of deep generative models. Moreover, we provide a theoretically grounded attack calibration technique, which consistently boosts the attack performance in all cases, across different attack settings, data modalities, and training configurations. We complement the systematic analysis of attack performance by a comprehensive experimental study, that investigates the effectiveness of various attacks w.r.t. model type and training configurations, over three diverse application scenarios (i.e., images, medical data, and location data).

PaperPDFCodeCode 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 22 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 13 ran (10 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DingfanChen/GAN-Leaks officialmentioned in papermentioned on GitHubtfMITSyntology: 22 samples, 13 ran (3 instrument-failed) · 9 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

22 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
7ran
9unverified

Licence: 5 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, 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 DingfanChen/GAN-Leaks. “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.

DingfanChen/GAN-Leaks official repository 22 samples, 13 ran (3 instrument-failed) · 9 unverified
adjust_dynamic_range in 7 papers gan_models/pggan/misc.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 90a97f8af1b8f269 · report fixture: signature data:ndarray/2/float, drange_in:tuple/1/float, drange_out:tuple/1/float · returned ndarray · level recorded 2026-09-22
conv_out_size_same in 7 papers gan_models/dcgan/model.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 40125e1efb67fa92 · report fixture: signature size:int/0/int, stride:int/0/int · returned int · level recorded 2026-09-22
create_image_grid in 6 papers gan_models/pggan/misc.py ran MIT (permissive) · cf03a3ce8cc3695e · report fixture: signature images:ndarray/4/float, grid_size:NoneType/0/? · returned ndarray · level recorded 2026-09-25
cset gan_models/pggan/networks.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · f7d82b02ff7c7fe1 · report fixture: signature cur_lambda:callable/0/?, new_cond:callable/0/?, new_lambda:callable/0/? · returned function · level recorded 2026-09-22
expand_path gan_models/dcgan/utils.py ran fingerprinted MIT (permissive) · c2e6e9b41af6cd71 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-25
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
gan_models/pggan/tfutil.py ran MIT (permissive) · 4e4ae70c11635981 · report fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-25
gen_random in 6 papers gan_models/dcgan/model.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 040714a23128cf94 · report fixture: signature mode:str/0/str, size:tuple/1/int · returned ndarray · level recorded 2026-09-22
ignore_unknown_theano_network gan_models/pggan/legacy.py ran MIT (permissive) · 2cd5be47220a5bc0 · report fixture: signature state:dict/0/? · returned dict · level recorded 2026-09-25
lerp in 27 papers
census: 4 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
gan_models/pggan/networks.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 0c45399f3741921e · report fixture: signature a:Tensor/2/float, b:Tensor/2/float, t:float/0/float · returned Tensor · level recorded 2026-09-22
lerp_clip in 8 papers gan_models/pggan/networks.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 6e81789f8f2068c8 · report fixture: signature a:EagerTensor/2/float, b:EagerTensor/2/float, t:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
read_image in 73 papers gan_models/dcgan/utils.py ran MIT (permissive) · 2c432d530ff1bcb3 · report fixture: signature filepath:str/0/str, resolution:int/0/int, cx:int/0/int, cy:int/0/int · returned ndarray · level recorded 2026-09-25
shape_to_list gan_models/pggan/tfutil.py ran MIT (permissive) · e963375233fe6dbe · report fixture: signature shape:list/1/MockDimension · returned list · level recorded 2026-09-25
timestamp in 15 papers gan_models/dcgan/utils.py ran MIT (permissive) · 221666d33a769cc9 · report fixture: signature s:str/0/str, ts:float/0/float · returned str · level recorded 2026-09-25
G_wgan_acgan gan_models/pggan/loss.py unverified MIT (permissive) · 82992ce1f4764e7b · report
conv2d in 119 papers gan_models/dcgan/ops.py unverified MIT (permissive) · 5d3ea24b351a5a12 · report
conv_cond_concat in 10 papers gan_models/dcgan/ops.py unverified MIT (permissive) · 2906e84dbebc3e14 · report
create_celebahq gan_models/pggan/dataset_tool.py unverified MIT (permissive) · c99617d8e7395b0f · report
deconv2d in 15 papers gan_models/dcgan/ops.py unverified MIT (permissive) · f1f0201f439514d5 · report
execute_cmdline in 9 papers gan_models/pggan/dataset_tool.py unverified MIT (permissive) · 81f0ed5010201398 · report
is_tf_expression gan_models/pggan/tfutil.py unverified MIT (permissive) · 574151db7f4e287b · report
parse_tfrecord_np gan_models/pggan/dataset.py unverified MIT (permissive) · 9a489c1c146c4e18 · report
parse_tfrecord_tf gan_models/pggan/dataset.py unverified MIT (permissive) · 490bcc28d486e9f7 · report

Tasks

Dataset GenerationInference AttackMembership Inference Attack

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