Papers › Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

27 Mar 2023arXiv:2303.15564archive 2025-07-28

Tao Sun, Lu Pang, Chao Chen, Haibin Ling

Deep neural networks are vulnerable to backdoor attacks, where an adversary maliciously manipulates the model behavior through overlaying images with special triggers. Existing backdoor defense methods often require accessing a few validation data and model parameters, which are impractical in many real-world applications, e.g., when the model is provided as a cloud service. In this paper, we address the practical task of blind backdoor defense at test time, in particular for black-box models. The true label of every test image needs to be recovered on the fly from a suspicious model regardless of image benignity. We focus on test-time image purification methods that incapacitate possible triggers while keeping semantic contents intact. Due to diverse trigger patterns and sizes, the heuristic trigger search in image space can be unscalable. We circumvent such barrier by leveraging the strong reconstruction power of generative models, and propose a framework of Blind Defense with Masked AutoEncoder (BDMAE). It detects possible triggers in the token space using image structural similarity and label consistency between the test image and MAE restorations. The detection results are then refined by considering trigger topology. Finally, we fuse MAE restorations adaptively into a purified image for making prediction. Our approach is blind to the model architectures, trigger patterns and image benignity. Extensive experiments under different backdoor settings validate its effectiveness and generalizability. Code is available at https://github.com/tsun/BDMAE.

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

Syntology 15 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 8 ran (8 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.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

tsun/bdmae officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 8 ran (0 instrument-failed) · 7 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

15 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 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 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 · honoured contract
7ran
7unverified

Licence: 3 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 tsun/bdmae. “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.

tsun/bdmae official repository 15 samples, 8 ran (0 instrument-failed) · 7 unverified
Februus_GTSRB models/februus.py ran MIT (permissive) · 66cb9e0f5d3c2483 · report fixture: signature n_channel:int/0/int · returned GTSRB · level recorded 2026-09-24
Februus_cifar10 models/februus.py ran MIT (permissive) · 44b42f1277dd9e3b · report fixture: signature n_channel:int/0/int · returned CIFAR · level recorded 2026-09-25
create_targets_bd attack/inputaware_attack.py ran MIT (permissive) · c296d9923af6a494 · report fixture: signature targets:Tensor/1/int, opt:OptConfig/0/? · returned Tensor · level recorded 2026-09-25
create_window in 82 papers defense/pytorch_ssim.py ran MIT (permissive) · 48b9ca43caa5a8d6 · report fixture: signature window_size:int/0/int, channel:int/0/int, sigma:float/0/float · returned Tensor · level recorded 2026-09-24
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
defense/pytorch_ssim.py ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
make_layers in 155 papers models/februus.py ran MIT (permissive) · 6470f17e85b4a1aa · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
poisson_blend_old defense/Februus.py ran MIT (permissive) · 7f8ea158f543bdb1 · report fixture: signature input:Tensor/4/float, output:Tensor/4/float, mask:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ssim in 112 papers defense/pytorch_ssim.py ran MIT (permissive) · d0b60b04b5634496 · report fixture: signature img1:Tensor/4/float, img2:Tensor/4/float, window_size:int/0/int, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-24
add_args in 42 papers attack/lc_attack.py unverified MIT (permissive) · 5394691602c74e1b · report
add_args in 42 papers attack/badnet_attack.py unverified MIT (permissive) · 47506a60457acdcf · report
fine_tuning defense/ft.py unverified MIT (permissive) · 8ade85bc4607042e · report
get_2d_sincos_pos_embed in 170 papers mae/pos_embed.py unverified MIT (permissive) here; the stored copy is pointer only · 3185afc3e87293ed · report
get_2d_sincos_pos_embed_from_grid in 140 papers mae/pos_embed.py unverified MIT (permissive) here; the stored copy is pointer only · f10004e059714d42 · report
newblend defense/Februus.py unverified MIT (permissive) · c56a11461aa35268 · report

Tasks

Image Generationbackdoor defense

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MAETest

1 archive method tag without a method page not shown.

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