Papers › Diffusion Models for Adversarial Purification

Diffusion Models for Adversarial Purification

16 May 2022arXiv:2205.07460archive 2025-07-28

Weili Nie, Brandon Guo, Yujia Huang, Chaowei Xiao, Arash Vahdat, Anima Anandkumar

Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the form of attack and the classification model, and thus can defend pre-existing classifiers against unseen threats. However, their performance currently falls behind adversarial training methods. In this work, we propose DiffPure that uses diffusion models for adversarial purification: Given an adversarial example, we first diffuse it with a small amount of noise following a forward diffusion process, and then recover the clean image through a reverse generative process. To evaluate our method against strong adaptive attacks in an efficient and scalable way, we propose to use the adjoint method to compute full gradients of the reverse generative process. Extensive experiments on three image datasets including CIFAR-10, ImageNet and CelebA-HQ with three classifier architectures including ResNet, WideResNet and ViT demonstrate that our method achieves the state-of-the-art results, outperforming current adversarial training and adversarial purification methods, often by a large margin. Project page: https://diffpure.github.io.

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

Syntology 23 code samples: 21 from 5 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 23: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 19 samples from 4 repositories, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 16 samples that ran have no recorded date.

NVlabs/DiffPure officialmentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
zshsh98/eps-ad mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score (arXiv:2305.16035; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

23 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · our draft was wrong
2ran; the contract check could not run
8ran
7unverified

Licence: 9 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. 2 samples are listed last, in a group without a repository. “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.

NVlabs/DiffPure official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
betas_for_alpha_bar in 123 papers guided_diffusion/gaussian_diffusion.py ran · honoured contract licence not identified · pointer only · 2ab2316ac6fdd869 · report fixture: signature num_diffusion_timesteps:int/0/int, alpha_bar:callable/0/?, max_beta:float/0/float · returned ndarray · level recorded, date not recorded
get_named_beta_schedule in 119 papers guided_diffusion/gaussian_diffusion.py ran · honoured contract licence not identified · pointer only · a086d6286a40b889 · report fixture: signature schedule_name:str/0/str, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded, date not recorded
point0bar1/ebm-defense found in paper text by Syntology 1 sample, 1 ran (0 instrument-failed) · 0 unverified
EBM nets.py ran · metamorphic tier: invariant licence not identified · pointer only · 53b522e213c74c83 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ermongroup/SDEdit found in paper text by Syntology 1 sample, 0 ran · 1 unverified
Model in 227 papers models/diffusion.py unverified MIT (permissive) · 3b923ff790cbbc0b · report
eladrich/pixel2style2pixel found in paper text by Syntology 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_keys in 26 papers models/psp.py ran · our draft was wrong MIT (permissive) · 29b9a890f149a3a6 · report fixture: signature d:dict/0/?, name:str/0/str · returned dict · level recorded 2026-09-22
run_on_batch in 6 papers predict.py unverified MIT (permissive) · a7def332eb991665 · report
chail/gan-ensembling found in paper text by Syntology 15 samples, 11 ran (3 instrument-failed) · 4 unverified
downsample in 59 papers networks/classifiers/attribute_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · a56784666af5bd6d · report fixture: signature images:Tensor/4/float, size:int/0/int · returned Tensor · level recorded 2026-09-22
format_time in 140 papers networks/classifiers/cifar10_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 8d7ec010c29e813b · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
get_logit networks/classifiers/attribute_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · a59556109795f95c · report fixture: signature net:callable/0/?, im:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_mean_and_std in 55 papers networks/classifiers/cifar10_utils.py ran · metamorphic tier: well formed MIT (permissive) here; the stored copy is pointer only · 3cbdd3b190b16350 · report fixture: signature dataset:MinimalDataset/0/? · returned tuple · level recorded 2026-09-22
lerp_clip in 8 papers networks/classifiers/attribute_classifier.py ran MIT (permissive) here; the stored copy is pointer only · 195d635db8eb778b · report fixture: signature a:Tensor/1/float, b:Tensor/1/float, t:Tensor/1/float · returned Tensor · level recorded 2026-09-24
max_res_from_state_dict networks/classifiers/attribute_classifier.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · d5eb57879ef1704e · report fixture: signature state_dict:dict/0/? · returned int · level recorded 2026-09-24
modify_layers utils/customnet.py ran fingerprinted MIT (permissive) · 8659b4900a4273d0 · report fixture: signature layers:list/1/tuple · returned list · level recorded 2026-09-24
polyinterp utils/LBFGS.py ran MIT (permissive) · a55a9c6d78060f5a · report fixture: signature points:ndarray/2/float, x_min_bound:float/0/float, x_max_bound:float/0/float, plot:bool/0/bool · returned float64 · level recorded 2026-09-24
postprocess in 70 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
networks/domain_classifier.py ran fingerprinted MIT (permissive) · 6774ed80906f2f42 · report fixture: signature classifier_output:Tensor/2/float · returned Tensor · level recorded 2026-09-24
state_dict_from_tf_parameters networks/classifiers/attribute_classifier.py ran MIT (permissive) · 1835534046b4b465 · report fixture: signature parameters:dict/0/? · returned dict · level recorded 2026-09-24
stylegan_setting networks/stylegan2/stylegan2_networks.py ran fingerprinted MIT (permissive) · 2f887a37af9d3f65 · report fixture: signature domain:str/0/str · returned dict · level recorded 2026-09-24
define_classifier networks/domain_classifier.py unverified MIT (permissive) · 41e902f9c7c2e2eb · report
define_generator networks/domain_generator.py unverified MIT (permissive) · 773b8b462df07b05 · report
get_softmaxed networks/classifiers/attribute_utils.py unverified MIT (permissive) · 839a62fe894a78a3 · report
is_legal in 5 papers utils/LBFGS.py unverified MIT (permissive) · 45be190c3dfd3c8f · report
Repository not located 2 samples, 1 ran (0 instrument-failed) · 1 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
betas_for_alpha_bar in 123 papers repository not located ran · honoured contract licence of this copy not recorded · 809d6a4eb92a37c4 · report fixture: signature num_diffusion_timesteps:int/0/int, alpha_bar:callable/0/?, max_beta:float/0/float · returned ndarray · level recorded, date not recorded
get_named_beta_schedule in 119 papers repository not located unverified licence of this copy not recorded · 3dfd61c7077a1607 · report

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for DiffPure (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for DiffPure (graph method: DiffPure). 8 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Model entry · level 0 · unverified · 3b923ff790cbbc0b
  2. AttnBlock model · level 1 · ran · bf6e2d1e65621c97
  3. Downsample model · level 1 · ran · f86ae8958e076367
  4. Normalize helper · level 1 · ran · our draft was wrong · c3a6b977022957cb
  5. ResnetBlock model · level 0 · unverified · 508610fafe221c17
  6. Upsample model · level 1 · ran · 726c85e75dfdfeb8
  7. get_timestep_embedding helper · level 1 · ran; the contract check could not run · cb49209c125de1b4
  8. nonlinearity helper · level 1 · ran · our draft was wrong · 3137073275f8c21a

harvested Assembly for DiffPure (graph method: DiffPure). 1 brick; individually on a fixture: 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. The assembly has not been run end-to-end.

one of 2 siblings

  1. EBM entry · level 1 · ran · 53b522e213c74c83

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="2205.07460") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Adversarial Purification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDiffusionDropoutGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionWide Residual BlockWideResNet

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