Papers › Opacus: User-Friendly Differential Privacy Library in PyTorch

Opacus: User-Friendly Differential Privacy Library in PyTorch

25 Sep 2021arXiv:2109.12298archive 2025-07-28

Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, Ilya Mironov

We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus.ai). Opacus is designed for simplicity, flexibility, and speed. It provides a simple and user-friendly API, and enables machine learning practitioners to make a training pipeline private by adding as little as two lines to their code. It supports a wide variety of layers, including multi-head attention, convolution, LSTM, GRU (and generic RNN), and embedding, right out of the box and provides the means for supporting other user-defined layers. Opacus computes batched per-sample gradients, providing higher efficiency compared to the traditional "micro batch" approach. In this paper we present Opacus, detail the principles that drove its implementation and unique features, and benchmark it against other frameworks for training models with differential privacy as well as standard PyTorch.

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

No sample from the archive's official repository (pytorch/opacus) is linked to this paper; the 12 samples below come from 2 community repositories. Syntology harvested code from pytorch/opacus for another paper.

pytorch/opacus: Syntology's graph links these samples to Large Language Models Can Be Strong Differentially Private Learners (arXiv:2110.05679; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 12 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 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 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community: 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.

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

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 3 samples that ran has no recorded date.

pytorch/opacus officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large Language Models Can Be Strong Differentially Private Learners (arXiv:2110.05679; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
alexbie98/dpgan-revisit mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (arXiv:1511.06434; that paper's own run record: 128 ran (of which 61 constructed an object rather than computing a result; 111 with no instrument failure: 3 honoured, 0 violated, 108 with no contract checked; 17 where Syntology's instrument failed) · 91 unverified); nothing checks that they implement this paper's method. report
woodyx218/private_vision mentioned on GitHubpytorchSyntology: 11 samples, 2 ran (1 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.

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

12 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 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.

2ran · honoured contract
1ran; the contract check could not run
9unverified

Licence: 0 of the 12 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.

woodyx218/private_vision community (archive-listed) 11 samples, 2 ran (1 instrument-failed) · 9 unverified
_compute_eps_cks private_vision/privacy_engine.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · dc7c6bd894c3af35 · report fixture: signature orders:ndarray/1/float, rdp:ndarray/1/float, delta:float/0/float · returned tuple · level recorded 2026-09-22
_get_sigma_with_target_epsilon private_vision/privacy_engine.py ran · honoured contract Apache-2.0 (permissive) · 0fc5cc5c20c50872 · report fixture: signature sigma_hi_init:float/0/float, sigma_lo_init:float/0/float, sigma_to_eps:callable/0/?, target_epsilon:float/0/float, threshold:float/0/float · returned float · level recorded 2026-09-22
PrivacyEngine private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 52ccc99b2a6cde9c · report
_eps_from_gdp private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 975a9efbff2d7c7a · report
_eps_from_glw private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 6a82b741a671c5d4 · report
_eps_from_rdp private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · bd9bd46c79d2c238 · report
_eps_from_rdp_cks private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 68999f7567ff1192 · report
get_sigma_from_gdp private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 12bce719b6a3b060 · report
get_sigma_from_glw private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 665dc7e22ef05056 · report
get_sigma_from_rdp private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · afe0f1fc95083e88 · report
get_sigma_from_rdp_cks private_vision/privacy_engine.py unverified Apache-2.0 (permissive) · 080da196349fb3a7 · report
meta-pytorch/opacus community 1 sample, 1 ran (0 instrument-failed) · 0 unverified
test in 377 papers examples/mnist.py ran · honoured contract Apache-2.0 (permissive) · dc66a9c5c516e132 · report fixture: signature model:callable/0/?, device:device/0/?, test_loader:TestLoaderWrapper/0/? · returned float · level recorded, date not recorded

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 Opacus (graph method: Opacus). 11 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. PrivacyEngine entry · level 0 · unverified · 52ccc99b2a6cde9c
  2. _eps_from_gdp helper · level 0 · unverified · 975a9efbff2d7c7a
  3. _eps_from_glw helper · level 0 · unverified · 6a82b741a671c5d4
  4. _eps_from_rdp helper · level 0 · unverified · bd9bd46c79d2c238
  5. _eps_from_rdp_cks helper · level 0 · unverified · 68999f7567ff1192
  6. get_sigma_from_gdp helper · level 0 · unverified · 12bce719b6a3b060
  7. get_sigma_from_glw helper · level 0 · unverified · 665dc7e22ef05056
  8. get_sigma_from_rdp helper · level 0 · unverified · afe0f1fc95083e88
  9. get_sigma_from_rdp_cks helper · level 0 · unverified · 080da196349fb3a7
  10. _compute_eps_cks helper · level 1 · ran; the contract check could not run (RAISES) · dc7c6bd894c3af35
  11. _get_sigma_with_target_epsilon helper · level 1 · ran · honoured contract · 0fc5cc5c20c50872

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="2109.12298") 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.

Methods

GRU

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