Papers › Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

18 Oct 2016arXiv:1610.05755archive 2025-07-28

Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the model may therefore reveal sensitive information. To address this problem, we demonstrate a generally applicable approach to providing strong privacy guarantees for training data: Private Aggregation of Teacher Ensembles (PATE). The approach combines, in a black-box fashion, multiple models trained with disjoint datasets, such as records from different subsets of users. Because they rely directly on sensitive data, these models are not published, but instead used as "teachers" for a "student" model. The student learns to predict an output chosen by noisy voting among all of the teachers, and cannot directly access an individual teacher or the underlying data or parameters. The student's privacy properties can be understood both intuitively (since no single teacher and thus no single dataset dictates the student's training) and formally, in terms of differential privacy. These properties hold even if an adversary can not only query the student but also inspect its internal workings. Compared with previous work, the approach imposes only weak assumptions on how teachers are trained: it applies to any model, including non-convex models like DNNs. We achieve state-of-the-art privacy/utility trade-offs on MNIST and SVHN thanks to an improved privacy analysis and semi-supervised learning.

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 (tensorflow/privacy) was not harvested; the 9 samples below come from 2 community repositories.

Syntology 9 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 2 repositories, 9 ran (3 with no instrument failure; 6 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tensorflow/privacy officialtfSyntology: not harvested report
aristizabal95/Making-PATE-Bidirecitonally-Private mentioned on GitHubpytorchSyntology: not harvested report
aristizabal95/Making-PATE-Bidirectionally-Private mentioned on GitHubpytorchSyntology: not harvested report
ashishdandekar/Privacy-at-risk mentioned on GitHubSyntology: 8 samples, 8 ran (5 instrument-failed) · 0 unverified report
chun-wei-ho/private-speech-adapter mentioned on GitHubtfApache-2.0Syntology: not harvested report
dimun/pate_torch mentioned on GitHubMITSyntology: not harvested report
hrsu/multiple_teachers mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
kamathhrishi/PATE mentioned on GitHubpytorchSyntology: 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.

Code Syntology ran Syntology

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 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
5ran; the contract check could not run

Licence: 9 of the 9 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.

ashishdandekar/Privacy-at-risk community (archive-listed) 8 samples, 8 ran (5 instrument-failed) · 0 unverified
PAR PATE/analysis.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 7644dcc3b6f870e3 · report fixture: signature e:float/0/float, e_0:float/0/float, gamma:float/0/float · returned float · level recorded 2026-09-22
build_logistic PATE/teachers.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 018c271d25bb072f · report fixture: signature x:ndarray/2/float, y:ndarray/1/int · returned LogisticRegression · level recorded 2026-09-22
build_model in 469 papers PATE/student.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · a3dad74681c7b99c · report fixture: signature x:ndarray/2/float, y:ndarray/1/int · returned LogisticRegression · level recorded 2026-09-22
compute_q_noisy_max PATE/analysis.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · c398a6682731556b · report fixture: signature counts:ndarray/1/float, noise_eps:float/0/float · returned float · level recorded 2026-09-22
generate_dataset in 41 papers PATE/student.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 68449dee88891420 · report fixture: signature x:ndarray/2/float, models:list/1/DecisionTreeClassifier, noise_eps:float/0/float, noise:bool/0/bool, local:bool/0/bool · returned tuple · level recorded 2026-09-22
logmgf_exact PATE/analysis.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · be23fce1736697e8 · report fixture: signature q:float/0/float, priv_eps:float/0/float, l:int/0/int · returned float · level recorded 2026-09-22
shuffle_data in 34 papers PATE/teachers.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 506614109988e897 · report fixture: signature x:ndarray/2/float, y:ndarray/1/int · returned tuple · level recorded 2026-09-22
split_data in 68 papers PATE/teachers.py ran; the contract check could not run (RAISES) GPL-3.0 (copyleft) · pointer only · b1ab84060a406b17 · report fixture: signature x:ndarray/2/float, y:ndarray/1/int · returned zip · level recorded 2026-09-22
hrsu/multiple_teachers community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
disturb differential_privacy1/differential_privacy/multiple_teachers/train_teachers.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 581c73d2f9b79b83 · report fixture: signature lists:list/1/int, rate:float/0/float · returned list · level recorded 2026-09-22

Tasks

Transfer Learning

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