Papers › Backdoor Attacks on Self-Supervised Learning

Backdoor Attacks on Self-Supervised Learning

21 May 2021CVPR 2022 1arXiv:2105.10123archive 2025-07-28

Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks - where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning, since the use of large unlabeled data makes data inspection to remove poisons prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a defense method based on knowledge distillation that succeeds in neutralizing the attack. Our code is available here: https://github.com/UMBCvision/SSL-Backdoor .

PaperPDFConference PDFCodeCode 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

Syntology 13 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (4 with no instrument failure; 5 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 11 samples that ran have no recorded date.

UMBCvision/SSL-Backdoor officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 9 ran (5 instrument-failed) · 2 unverified report
jsrdcht/SSL-Backdoor pytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
4ran; the contract check could not run
3ran
2unverified

Licence: 8 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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. 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.

UMBCvision/SSL-Backdoor official repository 11 samples, 9 ran (5 instrument-failed) · 2 unverified
buildLabelIndex in 8 papers rotnet/dataloader.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 57889d72f516d105 · report fixture: signature labels:list/1/int · returned dict · level recorded 2026-09-24
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
byol/methods/contrastive.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · ba00312b3d5b70dc · report fixture: returned Tensor · level recorded 2026-09-22
conv1x1 in 691 papers jigsaw/resnet.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers jigsaw/resnet.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
default_loader in 66 papers rotnet/jgg_dataset.py ran; the contract check could not run (DEP_MISSING) MIT (permissive) here; the stored copy is pointer only · 7bf07d5f59aae36d · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-25
getConfMatrixResults rotnet/utils.py ran fingerprinted MIT (permissive) · 3d9a20721d1cb559 · report fixture: signature matrix:ndarray/2/float · returned dict · level recorded 2026-09-25
get_head in 7 papers byol/model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 2d19f4f3143c2ccf · report fixture: signature out_size:int/0/int, cfg:Config/0/? · returned Sequential · level recorded 2026-09-22
pil_loader in 144 papers rotnet/jgg_dataset.py ran · honoured contract MIT (permissive) · f321f54723433661 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22
rotate_img in 7 papers rotnet/dataloader.py ran fingerprinted MIT (permissive) · 62681258109fb35d · report fixture: signature img:ndarray/3/int, rot:int/0/int · returned ndarray · level recorded 2026-09-25
accimage_loader in 47 papers rotnet/jgg_dataset.py unverified MIT (permissive) here; the stored copy is pointer only · 404fb2b2daa1ae78 · report
get_model in 368 papers byol/model.py unverified MIT (permissive) here; the stored copy is pointer only · 1d4261306685f800 · report
jsrdcht/SSL-Backdoor community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
create_torch_dataloader ssl_backdoor/attacks/badencoder/badencoder.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) licence of this copy not recorded · cf100d49bb98767a · report fixture: signature features:Tensor/2/float, labels:Tensor/1/int, batch_size:int/0/int · returned DataLoader · level recorded 2026-09-22
predict_feature ssl_backdoor/attacks/badencoder/badencoder.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) licence of this copy not recorded · 8c3820f76db73254 · report fixture: returned tuple · level recorded 2026-09-22

Tasks

Backdoor AttackInductive BiasKnowledge DistillationSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BYOLBatch NormalizationInfoNCEKnowledge DistillationMoCo

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