Papers › Membership Inference Attacks against Machine Learning Models

Membership Inference Attacks against Machine Learning Models

18 Oct 2016arXiv:1610.05820archive 2025-07-28

Reza Shokri, Marco Stronati, Congzheng Song, Vitaly Shmatikov

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform membership inference against a target model, we make adversarial use of machine learning and train our own inference model to recognize differences in the target model's predictions on the inputs that it trained on versus the inputs that it did not train on. We empirically evaluate our inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon. Using realistic datasets and classification tasks, including a hospital discharge dataset whose membership is sensitive from the privacy perspective, we show that these models can be vulnerable to membership inference attacks. We then investigate the factors that influence this leakage and evaluate mitigation strategies.

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

The archive's official repository (csong27/membership-inference) was not harvested; the 14 samples below come from 5 repositories the archive does not mark official.

Syntology 14 code samples harvested from 5 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 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: community (archive-listed): 11 samples from 4 repositories, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 3 samples 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

csong27/membership-inference officialSyntology: not harvested report
Koukyosyumei/AIJack mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Optimization in Heterogeneous Networks (arXiv:1812.06127; that paper's own run record: 15 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified), Label Leakage and Protection in Two-party Split Learning (arXiv:2102.08504; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and See through Gradients: Image Batch Recovery via GradInversion (arXiv:2104.07586; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
PrivPkt/PrivPkt mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
SAP-samples/security-research-membership-inference-and-differential-privacy mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Assessing differentially private deep learning with Membership Inference (arXiv:1912.11328; that paper's own run record: 1 ran (of which 0 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); nothing checks that they implement this paper's method. report
awslabs/sagemaker-privacy-for-nlp mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ml-research/do-not-trust-prediction-scores-for-membership-inference-attacks mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rupampatir/TrainingDataSynthesizer mentioned on GitHubtfSyntology: not harvested report
spring-epfl/mia mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yonsei-cysec/Membership_Inference_Attack mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
AdrienBenamira/membership_inference_attack pytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 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.

1ran · our draft was wrong
1ran; the contract check could not run
8ran
4unverified

Licence: 0 of the 14 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 5 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. 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.

PrivPkt/PrivPkt community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
force_length ISCX-preproc/kabab/utils/gen.py ran MIT (permissive) · 5ec7cc132db252da · report fixture: signature iterable:generator/0/?, n:int/0/int, pad:int/0/int · returned list · level recorded 2026-09-26
get_base_pkt ISCX-preproc/kabab/flow.py ran MIT (permissive) · 9a16013f7255867e · report fixture: signature cap:list/1/Tensor · returned Tensor · level recorded 2026-09-26
get_pcaps ISCX-preproc/kabab/utils/general.py ran MIT (permissive) · d16121d6ebb3bc1c · report fixture: signature data_dir:MockPath/0/? · returned list · level recorded 2026-09-26
give_me_results mia/mia.py ran MIT (permissive) · d54e16609e4cd4a4 · report fixture: signature attack_guesses:ndarray/1/int, real_membership_labels:ndarray/1/int · returned list · level recorded 2026-09-26
load_pcap ISCX-preproc/kabab/utils/general.py unverified MIT (permissive) · 21786ee5f33906cd · report
ml-research/do-not-trust-prediction-scores-for-membership-inference-attacks community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_model_prediction_scores utils/model_utils.py ran MIT (permissive) · af19edeb92a0ce40 · report fixture: signature model:callable/0/?, apply_softmax:bool/0/bool, dataset:list/1/tuple, batch_size:int/0/int, num_workers:int/0/int · returned Tensor · level recorded 2026-09-26
spring-epfl/mia community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
prepare_attack_data mia/estimators.py ran · our draft was wrong MIT (permissive) · f399cccee25a4712 · report fixture: signature model:SimpleClassifier/0/?, data_in:tuple/1/ndarray, data_out:tuple/1/ndarray · returned tuple · level recorded 2026-09-22
yonsei-cysec/Membership_Inference_Attack community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils/metric.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · b0f936d4d6ae3b8c · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded, date not recorded
lira_metrics utils/metric.py ran MIT (permissive) · 7731cfa4bb088988 · report fixture: signature output:ndarray/2/int, target:ndarray/2/int, bool_average:bool/0/bool, num_classes:int/0/int · returned tuple · level recorded 2026-09-26
load_config in 389 papers utils/load_config.py ran MIT (permissive) · ddfeb2a10eaefde7 · report fixture: signature config_name:str/0/str, config_path:str/0/str · returned EasyDict · level recorded 2026-09-26
make_member_nonmember shadow/make_data.py unverified MIT (permissive) · d697fc8dd59df530 · report
Lasagne/Recipes found in paper text by Syntology 3 samples, 1 ran (0 instrument-failed) · 2 unverified
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
modelzoo/inception_v3.py ran fingerprinted MIT (permissive) · 1dff06f483218f63 · report fixture: signature im:ndarray/3/float · returned ndarray · level recorded 2026-09-25
convert_back modelzoo/c3d.py unverified MIT (permissive) · 1ed624f64c635c68 · report
load_dataset in 276 papers papers/densenet/cifar10.py unverified MIT (permissive) · 5206fe60bb83055f · report

Tasks

BIG-bench Machine LearningGeneral ClassificationInference 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