Papers › Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

22 Feb 2022arXiv:2202.11202archive 2025-07-28

Hao He, Kaiwen Zha, Dina Katabi

Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of contrastive learning. We propose Contrastive Poisoning (CP), the first effective such attack on CL. We empirically show that Contrastive Poisoning, not only drastically reduces the performance of CL algorithms, but also attacks supervised learning models, making it the most generalizable indiscriminate poisoning attack. We also show that CL algorithms with a momentum encoder are more robust to indiscriminate poisoning, and propose a new countermeasure based on matrix completion. Code is available at: https://github.com/kaiwenzha/contrastive-poisoning.

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 18 code samples harvested from 1 repository linked to this paper: 13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 13 ran (9 with no instrument failure; 4 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 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.

kaiwenzha/contrastive-poisoning officialmentioned on GitHubpytorchSyntology: 18 samples, 13 ran (4 instrument-failed) · 5 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: 13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 5 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.

4ran · our draft was wrong
9ran
5unverified

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 kaiwenzha/contrastive-poisoning. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

kaiwenzha/contrastive-poisoning official repository 18 samples, 13 ran (4 instrument-failed) · 5 unverified
BYOL model.py ran · metamorphic tier: deterministic MIT (permissive) · f5329be21bc798d0 · report fixture: returned BYOL · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · e93841d2aa94ddad · report fixture: returned BasicBlock · level recorded 2026-09-22
Bottleneck in 98 papers model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 613844ebc89b237b · report fixture: returned Bottleneck · level recorded 2026-09-22
ResNet in 139 papers model.py ran fingerprinted MIT (permissive) · 396b12c0d690c96b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ResNetNoHead model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · bb2b7357a288f84c · report fixture: returned ResNetNoHead · level recorded 2026-09-22
ResNetWithHead model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2e47d5200e06bb5d · report fixture: returned ResNetWithHead · level recorded 2026-09-22
TextFormat model.py ran MIT (permissive) · dd9595263567cf07 · report fixture: signature text:str/0/str, color:str/0/str · returned str · level recorded 2026-09-24
_get_byol_mlp model.py ran · our draft was wrong MIT (permissive) · fc4d4f310d9bfc0e · report fixture: signature num_ftrs:int/0/int, hidden_dim:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-22
log in 61 papers
census: 10 implementations from 16 papers, 7 distinct outputs on one shared input
model.py ran · our draft was wrong MIT (permissive) · 0f408c13a7b48d93 · report fixture: signature text:str/0/str, color:str/0/str, style:str/0/str, with_time:bool/0/bool, handle:StringIO/0/? · returned str · level recorded 2026-09-22
resnet101 in 24 papers model.py ran · metamorphic tier: deterministic MIT (permissive) · 188a542bb3d0c413 · report fixture: returned ResNet · level recorded 2026-09-22
resnet18 in 432 papers model.py ran · our draft was wrong MIT (permissive) · 907fb9d80310a75f · report fixture: signature in_channel:int/0/int, zero_init_residual:bool/0/bool · returned ResNet · level recorded 2026-09-22
resnet34 in 148 papers model.py ran · our draft was wrong MIT (permissive) · b5e082eee874ab6a · report fixture: signature in_channel:int/0/int, zero_init_residual:bool/0/bool · returned ResNet · level recorded 2026-09-22
resnet50 in 121 papers model.py ran · metamorphic tier: deterministic MIT (permissive) · bc02a35848587cf8 · report fixture: returned ResNet · level recorded 2026-09-22
AttackModel model.py unverified MIT (permissive) · 3e90e9281a3090fb · report
MoCo in 12 papers model.py unverified MIT (permissive) · 3806b767e591b869 · report
_MomentumEncoderMixin model.py unverified MIT (permissive) · de6d1a439b0eb3ae · report
_deactivate_requires_grad model.py unverified MIT (permissive) · d2c729d46218e6c7 · report
_do_momentum_update model.py unverified MIT (permissive) · 9ff781762297580d · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Contrastive Poisoning (CP) (graph method: Contrastive Poisoning (CP)). 19 bricks; individually on a fixture: 13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. AttackModel entry · level 0 · unverified · 3e90e9281a3090fb
  2. BYOL helper · level 1 · ran · f5329be21bc798d0
  3. MoCo helper · level 0 · unverified · 3806b767e591b869
  4. ResNetNoHead helper · level 1 · ran · bb2b7357a288f84c
  5. ResNetWithHead helper · level 1 · ran · 2e47d5200e06bb5d
  6. _MomentumEncoderMixin helper · level 0 · unverified · de6d1a439b0eb3ae
  7. _get_byol_mlp helper · level 1 · ran · our draft was wrong · fc4d4f310d9bfc0e
  8. concat_all_gather helper · level 0 · unverified · 73cecca9f3575f09
  9. _deactivate_requires_grad helper · level 0 · unverified · d2c729d46218e6c7
  10. _do_momentum_update helper · level 0 · unverified · 9ff781762297580d
  11. BasicBlock helper · level 1 · ran · e93841d2aa94ddad
  12. Bottleneck helper · level 1 · ran · 613844ebc89b237b
  13. ResNet helper · level 1 · ran · 396b12c0d690c96b
  14. TextFormat helper · level 1 · ran · dd9595263567cf07
  15. log helper · level 1 · ran · our draft was wrong · 0f408c13a7b48d93
  16. resnet101 helper · level 1 · ran · 188a542bb3d0c413
  17. resnet18 helper · level 1 · ran · our draft was wrong · 907fb9d80310a75f
  18. resnet34 helper · level 1 · ran · our draft was wrong · b5e082eee874ab6a
  19. resnet50 helper · level 1 · ran · bc02a35848587cf8

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="2202.11202") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningData AugmentationData PoisoningMatrix Completion

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBYOLBatch NormalizationBottleneck Residual BlockColorJitterContrastive LearningConvolutionDense ConnectionsFeedforward NetworkGlobal Average PoolingInfoNCEKaiming InitializationMax PoolingMoCoNT-XentRandom Gaussian BlurRandom Resized CropReLUResidual BlockResidual ConnectionSimCLR

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