Papers › Formalizing Distribution Inference Risks

Formalizing Distribution Inference Risks

7 Jun 2021arXiv:2106.03699archive 2025-07-28

Anshuman Suri, David Evans

Property inference attacks reveal statistical properties about a training set but are difficult to distinguish from the primary purposes of statistical machine learning, which is to produce models that capture statistical properties about a distribution. Motivated by Yeom et al.'s membership inference framework, we propose a formal and generic definition of property inference attacks. The proposed notion describes attacks that can distinguish between possible training distributions, extending beyond previous property inference attacks that infer the ratio of a particular type of data in the training data set. In this paper, we show how our definition captures previous property inference attacks as well as a new attack that reveals the average degree of nodes of a training graph and report on experiments giving insight into the potential risks of property inference attacks.

PaperPDFCodeCode Syntology ranMethod as code

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 16 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 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.

iamgroot42/distribution_inference officialmentioned in paperpytorchMITSyntology: 15 samples, 10 ran (3 instrument-failed) · 5 unverified report
epfl-dlab/property-inference-attacks mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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

16 samples harvested: 11 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 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 · our draft was wrong
8ran
5unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

iamgroot42/distribution_inference official repository 15 samples, 10 ran (3 instrument-failed) · 5 unverified
find_to_prune_for_mean_degree arxiv/data_utils.py ran · our draft was wrong MIT (permissive) · 6eff479cbea3e29a · report fixture: signature g:MockGraph/0/?, degs:ndarray/1/float, wanted_deg:float/0/float, pre_prune:list/1/empty · returned list · level recorded 2026-09-22
find_to_prune_for_threshold_degree arxiv/data_utils.py ran · our draft was wrong MIT (permissive) · f40e50279ebbef17 · report fixture: signature g:SimpleGraph/0/?, degs:ndarray/1/int, threshold_degree:int/0/int, pre_prune:list/1/empty · returned list · level recorded 2026-09-22
get_model in 368 papers census/model_utils.py ran MIT (permissive) · af02646c3c6280d9 · report fixture: signature max_iter:int/0/int, hidden_layer_sizes:tuple/1/int · returned MLPClassifier · level recorded 2026-09-25
get_model_folder_path boneage/model_utils.py ran fingerprinted MIT (permissive) · a14eb1059b998b40 · report fixture: signature split:str/0/str, ratio:str/0/str · returned str · level recorded 2026-09-25
get_model_preds arxiv/perf_tests.py ran MIT (permissive) · 99824846ec38d874 · report fixture: signature models:list/1/callable, ds:MinimalDataset/0/? · returned tuple · level recorded 2026-09-25
load_all_loader_data utils.py ran MIT (permissive) · 744d18d79255848c · report fixture: signature data_loader:list/1/tuple · returned tuple · level recorded 2026-09-25
neighbor_removal arxiv/data_utils.py ran · our draft was wrong MIT (permissive) · aff1bea8d51561a3 · report fixture: signature g:MockGraph/0/?, pick:int/0/int, degs:ndarray/1/int, inf_val:int/0/int · returned ndarray · level recorded 2026-09-22
scaled_values utils.py ran MIT (permissive) · 0d35d1ccf120ef81 · report fixture: signature val:ndarray/2/float, mean:ndarray/1/float, std:ndarray/1/float, eps:float/0/float · returned ndarray · level recorded 2026-09-25
test in 377 papers arxiv/model_utils.py ran MIT (permissive) · 402b17de9d91f42e · report fixture: signature model:callable/0/?, ds:SimpleDataset/0/?, train_idx:Tensor/1/int, test_idx:Tensor/1/int, evaluator:SimpleEvaluator/0/? · returned tuple · level recorded 2026-09-25
train_model in 103 papers arxiv/meta_regress.py ran MIT (permissive) · 2c02460ce32daf02 · report fixture: signature model:callable/0/?, train_data:tuple/1/list, test_data:tuple/1/list, eval_every:int/0/int, epochs:int/0/int, lr:float/0/float, binary:bool/0/bool, regression:bool/0/bool, save_every:int/0/int · returned SimpleModel · level recorded 2026-09-25
extract_model_weights arxiv/meta_regress.py unverified MIT (permissive) · 706ebea7a9142d87 · report
get_model_representations census/model_utils.py unverified MIT (permissive) · 78e3c2d0b8ee5189 · report
layer_output census/model_utils.py unverified MIT (permissive) · 713f29bfaa8a9630 · report
load_model in 479 papers boneage/model_utils.py unverified MIT (permissive) · b0d543ba1f0f69c7 · report
train in 522 papers arxiv/model_utils.py unverified MIT (permissive) · 5e91ee8bb1615456 · report
epfl-dlab/property-inference-attacks community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DeepSets propinfer/deepsets.py ran MIT (permissive) · f69ab921c74d20dd · report fixture: returned DeepSets · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for a formal and generic definition of property inference attacks (graph method: a formal and generic definition of property inference attacks). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. DeepSets entry · level 1 · ran · f69ab921c74d20dd

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.03699") returns these assemblies with each brick's role and wiring (how to connect).

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