Papers › Revisiting Membership Inference Under Realistic Assumptions

Revisiting Membership Inference Under Realistic Assumptions

21 May 2020arXiv:2005.10881archive 2025-07-28

Bargav Jayaraman, Lingxiao Wang, Katherine Knipmeyer, Quanquan Gu, David Evans

We study membership inference in settings where some of the assumptions typically used in previous research are relaxed. First, we consider skewed priors, to cover cases such as when only a small fraction of the candidate pool targeted by the adversary are actually members and develop a PPV-based metric suitable for this setting. This setting is more realistic than the balanced prior setting typically considered by researchers. Second, we consider adversaries that select inference thresholds according to their attack goals and develop a threshold selection procedure that improves inference attacks. Since previous inference attacks fail in imbalanced prior setting, we develop a new inference attack based on the intuition that inputs corresponding to training set members will be near a local minimum in the loss function, and show that an attack that combines this with thresholds on the per-instance loss can achieve high PPV even in settings where other attacks appear to be ineffective. Code for our experiments can be found here: https://github.com/bargavj/EvaluatingDPML.

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 18 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 14 ran (14 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

bargavj/EvaluatingDPML officialmentioned in papermentioned on GitHubtfMITSyntology: 18 samples, 14 ran (0 instrument-failed) · 4 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

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 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.

14ran
4unverified

Licence: 0 of the 18 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 bargavj/EvaluatingDPML. “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.

bargavj/EvaluatingDPML official repository 18 samples, 14 ran (0 instrument-failed) · 4 unverified
adv_lim improved_mi/interpret_results.py ran fingerprinted MIT (permissive) · 6ae7aa8ecd940dba · report fixture: signature eps:float/0/float, delta:float/0/float, alpha:float/0/float · returned float64 · level recorded 2026-09-25
compute_gdp_mu core/privacy_accountant.py ran MIT (permissive) · c4dafd15e67d5b6d · report fixture: signature sampling_rate:float/0/float, sigma:float/0/float, steps:int/0/int · returned float64 · level recorded 2026-09-25
f in 68 papers
census: 17 implementations from 15 papers, 17 distinct outputs across 7 buckets, one shared input per bucket
improved_mi/interpret_results.py ran fingerprinted MIT (permissive) · 013948fc6c807e9c · report fixture: signature eps:float/0/float, delta:float/0/float, alpha:float/0/float · returned float64 · level recorded 2026-09-25
filePatternTest extra/crawl_census_data.py ran MIT (permissive) · 69b6be2d4e95ab76 · report fixture: signature string:str/0/str · returned bool · level recorded 2026-09-25
get_gdp_privacy_spent core/privacy_accountant.py ran MIT (permissive) · 9d391b1461c8bac7 · report fixture: signature mu:float/0/float, target_delta:float/0/float · returned tuple · level recorded 2026-09-25
get_layer_outputs core/classifier.py ran MIT (permissive) · 52ed89b6b5acac75 · report fixture: signature predictions:generator/0/? · returned ndarray · level recorded 2026-09-25
get_ppv core/utilities.py ran MIT (permissive) · dfe0c2fa5470175b · report fixture: signature mem:ndarray/1/int, pred:ndarray/1/int · returned float64 · level recorded 2026-09-25
get_ppv evaluating_dpml/interpret_results.py ran MIT (permissive) · 1fb8971949a71f06 · report fixture: signature mem:ndarray/1/int, pred:ndarray/1/int · returned float64 · level recorded 2026-09-25
get_ppvs core/utilities.py ran fingerprinted MIT (permissive) · 413865dc2f6548ce · report fixture: signature ref:ndarray/1/float, vec:ndarray/1/float · returned ndarray · level recorded 2026-09-25
get_predictions in 17 papers core/classifier.py ran MIT (permissive) · 3e9f698a4d78f018 · report fixture: signature predictions:generator/0/? · returned tuple · level recorded 2026-09-25
load_attack_data core/data_util.py ran MIT (permissive) · 4deba715a71e9fb9 · report fixture: signature MODEL_PATH:str/0/str · returned tuple · level recorded 2026-09-25
pretty_position core/utilities.py ran MIT (permissive) · e9b48ac076c43238 · report fixture: signature X:ndarray/1/float, Y:ndarray/1/float, pos:int/0/int · returned tuple · level recorded 2026-09-25
process_features core/data_util.py ran MIT (permissive) · 148e8c52e944a4d1 · report fixture: signature features:ndarray/2/float, dataset:str/0/str, attribute_dict:dict/0/?, max_attr_vals:dict/0/?, target_attr:str/0/str, col_flags:dict/0/?, skip_sensitive:bool/0/bool, skip_corr:bool/0/bool · returned ndarray · level recorded 2026-09-25
theoretical_limit evaluating_dpml/interpret_results.py ran fingerprinted MIT (permissive) · 31e6eedc77b79b03 · report fixture: signature epsilons:list/1/float · returned list · level recorded 2026-09-25
get_result in 30 papers improved_ai/interpret_results.py unverified MIT (permissive) · 13622d0e53332de3 · report
isFilePresent extra/crawl_census_data.py unverified MIT (permissive) · dad29b3471246eeb · report
load_data in 700 papers core/data_util.py unverified MIT (permissive) · 17697fa3fcb82caa · report
ppv_lim improved_mi/interpret_results.py unverified MIT (permissive) · f18eacb739286d78 · report

Tasks

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