Papers › Deep Learning with Differential Privacy

Deep Learning with Differential Privacy

1 Jul 2016arXiv:1607.00133archive 2025-07-28

Martín Abadi, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models should not expose private information in these datasets. Addressing this goal, we develop new algorithmic techniques for learning and a refined analysis of privacy costs within the framework of differential privacy. Our implementation and experiments demonstrate that we can train deep neural networks with non-convex objectives, under a modest privacy budget, and at a manageable cost in software complexity, training efficiency, and model quality.

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

No sample from the archive's official repository (tensorflow/models) is linked to this paper; the 24 samples below come from 4 community repositories. Syntology harvested code from tensorflow/models for 4 other papers.

tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 24 code samples harvested from 4 repositories linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 1 violated, 18 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 24 samples from 4 repositories, 22 ran (19 with no instrument failure; 3 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 10 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.

26 repositories listed; official and paper-mentioned ones first.

tensorflow/models officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
AshwinRJ/Federated-Learning-PyTorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Learning: Challenges, Methods, and Future Directions (arXiv:1908.07873; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
BRAIN-chain/FRAIN mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Learning: Challenges, Methods, and Future Directions (arXiv:1908.07873; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ChrisWaites/pyvacy mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: 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
SAP-samples/machine-learning-diff-private-federated-learning mentioned on GitHubtfSyntology: not harvested report
SAP/machine-learning-diff-private-federated-learning mentioned on GitHubtfSyntology: not harvested report
SayedMaheen/60DaysOfUdacity mentioned on GitHubpytorchSyntology: not harvested report
apple/ml-flair mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
cyrusgeyer/DiffPrivate_FedLearning mentioned on GitHubtfSyntology: not harvested report
dayu11/Differentially-Private-Deep-Learning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large Scale Private Learning via Low-rank Reparametrization (arXiv:2106.09352; that paper's own run record: 4 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; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
facebookresearch/pytorch-dp mentioned 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
fritz-max/replicating-1607.00133 mentioned on GitHubpytorchSyntology: not harvested report
ftramer/Handcrafted-DP mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2206.07136 (its page on Syntology; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
mayank5695/Differential-Privacy mentioned on GitHubtfSyntology: not harvested report
michelle0924hhx/DiffPrivate_FedLearning mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Communication-Efficient Learning of Deep Networks from Decentralized Data (arXiv:1602.05629; that paper's own run record: 47 ran (of which 17 constructed an object rather than computing a result; 27 with no instrument failure: 2 honoured, 0 violated, 25 with no contract checked; 20 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
owkin/grad-cnns mentioned on GitHubpytorchSyntology: not harvested report
s-huu/pmtl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Ditto: Fair and Robust Federated Learning Through Personalization (arXiv:2012.04221; that paper's own run record: 15 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 7 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
sapmlresearch/DiffPrivate_FedLearning mentioned on GitHubtfSyntology: not harvested report
sunblaze-ucb/dpml-benchmark mentioned on GitHubtfMITSyntology: 15 samples, 14 ran (0 instrument-failed) · 1 unverified report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
trusthlt/dp-nmt mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DP-NMT: Scalable Differentially-Private Machine Translation (arXiv:2311.14465; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
trusthlt/granularity-is-crucial-dp mentioned on GitHubjaxApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
woodyx218/opacus_global_clipping mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
zzzer1019/FL_DP mentioned on GitHubtfSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
code-implementation1/Code9 mindsporeSyntology: 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

24 samples harvested: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 1 violated, 18 with no contract checked; 3 where Syntology's instrument failed) · 2 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 · violated contract
3ran · our draft was wrong
18ran
2unverified

Licence: 3 of the 24 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 4 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.

sunblaze-ucb/dpml-benchmark community (archive-listed) 15 samples, 14 ran (0 instrument-failed) · 1 unverified
build_binary_ys gridsearch.py ran MIT (permissive) · 636d2d70184406df · report fixture: signature vec_ys:ndarray/2/int · returned list · level recorded 2026-09-26
clip_rows common/clipping.py ran MIT (permissive) · 055e3c60e4826989 · report fixture: signature data:csr_matrix/2/float, ord:int/0/int, L:int/0/int · returned csr_matrix · level recorded 2026-09-26
compute_alpha in 26 papers algorithms/frank_wolfe.py ran MIT (permissive) · d9a28ecc659a537a · report fixture: signature corner_size:float/0/float, gradient:float/0/float, m:int/0/int, noise_para:float/0/float, theta:NoneType/0/? · returned list · level recorded 2026-09-26
compute_classification_counts common/common.py ran MIT (permissive) · f0e8aa3d25432f87 · report fixture: signature x:ndarray/2/float, y:ndarray/1/int, theta:ndarray/1/float · returned tuple · level recorded 2026-09-26
compute_multiclass_counts common/common.py ran MIT (permissive) · ff50dd3563228c04 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, thetas:list/1/Tensor · returned tuple · level recorded 2026-09-26
constrain_l2_norm common/constraints.py ran fingerprinted MIT (permissive) · 48efe13866a9810d · report fixture: signature theta:ndarray/1/float, constraint:float/0/float · returned ndarray · level recorded 2026-09-26
constrain_to_unit_ball common/common.py ran fingerprinted MIT (permissive) · 664f0e18e9133aed · report fixture: signature theta:ndarray/1/float · returned ndarray · level recorded 2026-09-26
constrain_to_unit_ball common/constraints.py ran fingerprinted MIT (permissive) · 6b151b2baef4dec8 · report fixture: signature theta:ndarray/1/float · returned ndarray · level recorded 2026-09-26
dict_product in 8 papers gridsearch.py ran MIT (permissive) · 03cc2bf621d7826a · report fixture: signature dicts:dict/0/? · returned generator · level recorded 2026-09-26
gen_random_vector_in_unit_ball common/constraints.py ran MIT (permissive) · 6d88e181355723bb · report fixture: signature size:tuple/1/int · returned ndarray · level recorded 2026-09-26
get_max_norm common/clipping.py ran MIT (permissive) · 4184d0c4bb83a53e · report fixture: signature data:csr_matrix/2/float, ord:int/0/int · returned float64 · level recorded 2026-09-26
get_norm in 48 papers common/clipping.py ran MIT (permissive) · a9e9e7baf4bbeecd · report fixture: signature data:csr_matrix/2/int, ord:int/0/int · returned float64 · level recorded 2026-09-26
private_frank_wolfe algorithms/frank_wolfe.py ran MIT (permissive) · 1859aa1574ad821e · report fixture: signature x:ndarray/2/float, y:ndarray/1/float, loss_gradient:callable/0/?, eps:float/0/float, delta:float/0/float, step_size:int/0/int, num_iters:int/0/int, constraint:int/0/int, L:int/0/int · returned ndarray · level recorded 2026-09-26
random_projection common/datasets.py ran fingerprinted MIT (permissive) · 329c267465c93b73 · report fixture: signature ori_matrix:ndarray/2/float, k:int/0/int · returned ndarray · level recorded 2026-09-26
amp_run_classification algorithms/approximate_minima_perturbation.py unverified MIT (permissive) · 18dd5d7fb77b0965 · report
trusthlt/granularity-is-crucial-dp community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
decode_postprocess_text utils.py ran Apache-2.0 (permissive) · eced2545684e00aa · report fixture: signature tokenizer:MockTokenizer/0/?, predictions:Tensor/2/int, labels:Tensor/2/int · returned tuple · level recorded 2026-09-24
numpy_collate in 11 papers utils.py ran Apache-2.0 (permissive) · 2d04dae1de533b58 · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-24
sacre_bleu_postprocess_text utils.py ran Apache-2.0 (permissive) · 94bee6b69f7ebc31 · report fixture: signature predictions:list/1/str, labels:list/1/str · returned tuple · level recorded 2026-09-24
str2bool in 533 papers flags_attack.py ran · violated contract Apache-2.0 (permissive) · 387318c7a376d775 · report fixture: signature val:str/0/str · returned bool · level recorded 2026-09-22
wrap_collate_with_empty dataloader.py ran Apache-2.0 (permissive) · 1f6e34e8d7e65cec · report fixture: signature collate_fn:callable/0/? · returned function · level recorded 2026-09-24
woodyx218/opacus_global_clipping community (archive-listed) 1 sample, 0 ran · 1 unverified
test in 377 papers examples/mnist.py unverified Apache-2.0 (permissive) · 0084ec1c2df6dc92 · report
zzzer1019/FL_DP community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
Vname_to_FeedPname Helper_Functions.py ran · our draft was wrong no licence file found · pointer only · 4b5f34895003fc5f · report fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22
Vname_to_Pname Helper_Functions.py ran · our draft was wrong no licence file found · pointer only · 96ac62e9e705aa09 · report fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22
create_save_dir in 7 papers Helper_Functions.py ran · our draft was wrong no licence file found · pointer only · f466d758bb1dc678 · report fixture: signature FLAGS:FLAGS/0/? · returned str · level recorded 2026-09-22

Tasks

BIG-bench Machine LearningDeep 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