Papers › One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks

One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks

24 May 2022arXiv:2205.12141archive 2025-07-28

Shutong Wu, Sizhe Chen, Cihang Xie, Xiaolin Huang

Unlearnable examples (ULEs) aim to protect data from unauthorized usage for training DNNs. Existing work adds ℓ_∞-bounded perturbations to the original sample so that the trained model generalizes poorly. Such perturbations, however, are easy to eliminate by adversarial training and data augmentations. In this paper, we resolve this problem from a novel perspective by perturbing only one pixel in each image. Interestingly, such a small modification could effectively degrade model accuracy to almost an untrained counterpart. Moreover, our produced One-Pixel Shortcut (OPS) could not be erased by adversarial training and strong augmentations. To generate OPS, we perturb in-class images at the same position to the same target value that could mostly and stably deviate from all the original images. Since such generation is only based on images, OPS needs significantly less computation cost than the previous methods using DNN generators. Based on OPS, we introduce an unlearnable dataset called CIFAR-10-S, which is indistinguishable from CIFAR-10 by humans but induces the trained model to extremely low accuracy. Even under adversarial training, a ResNet-18 trained on CIFAR-10-S has only 10.61% accuracy, compared to 83.02% by the existing error-minimizing method.

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 18 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 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: 3 where our contract draft was wrong; 1 where the contract check could not run; 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. 1 of the 13 samples that ran has no recorded date.

cychomatica/one-pixel-shotcut officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 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 0 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
1ran; the contract check could not run
9ran
5unverified

Licence: 3 of the 18 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 cychomatica/one-pixel-shotcut. “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.

cychomatica/one-pixel-shotcut official repository 18 samples, 13 ran (4 instrument-failed) · 5 unverified
Densenet121 model/DenseNet.py ran Apache-2.0 (permissive) · a2b0fd19f9050594 · report fixture: signature num_classes:int/0/int · returned DenseNet · level recorded 2026-09-24
Densenet169 model/DenseNet.py ran Apache-2.0 (permissive) · 020eefbf270b4c86 · report fixture: signature num_classes:int/0/int · returned DenseNet · level recorded 2026-09-24
Densenet201 model/DenseNet.py ran Apache-2.0 (permissive) · 85e9b46978ad9fdc · report fixture: signature num_classes:int/0/int · returned DenseNet · level recorded 2026-09-24
ResNet18 in 174 papers model/ResNet.py ran Apache-2.0 (permissive) · ff9d88e7227f5564 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
ResNet34 in 91 papers model/ResNet.py ran Apache-2.0 (permissive) · ca1d217d7ca5ddf4 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
ResNet50 in 83 papers model/ResNet.py ran Apache-2.0 (permissive) · 71455bb26f47a8a0 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
VGG11 in 36 papers model/VGG.py ran Apache-2.0 (permissive) · e4759822cc516831 · report fixture: signature batch_norm:bool/0/bool, num_classes:int/0/int · returned VGG · level recorded 2026-09-24
VGG13 in 25 papers model/VGG.py ran Apache-2.0 (permissive) · 885b135d492f1a82 · report fixture: signature batch_norm:bool/0/bool, num_classes:int/0/int · returned VGG · level recorded 2026-09-24
conv3x3 in 1,376 papers model/WideResNet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 00e569acd6b45ef0 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
make_layers in 155 papers model/VGG.py ran · our draft was wrong Apache-2.0 (permissive) · ac62432dc5134b0d · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
mixup_criterion in 28 papers augmentation/Mixup.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 97f484048ac03556 · report fixture: signature criterion:callable/0/?, pred:Tensor/2/float, y_a:Tensor/1/int, y_b:Tensor/1/int, lam:float/0/float · returned Tensor · level recorded 2026-09-22
mixup_data in 51 papers augmentation/Mixup.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic Apache-2.0 (permissive) here; the stored copy is pointer only · 8897714b1e9b6396 · report fixture: signature x:Tensor/2/float, y:Tensor/1/int, alpha:float/0/float, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-22
net_param_diff_norm utils.py ran Apache-2.0 (permissive) · 6d2cddc06920551f · report fixture: signature model:callable/0/?, state_dict_init:dict/0/?, p:str/0/str · returned float32 · level recorded 2026-09-24
load_cifar100_data utils.py unverified Apache-2.0 (permissive) · 042cdc9057142cfc · report
load_cifar10_data utils.py unverified Apache-2.0 (permissive) · b1ebcb3950081b8d · report
mixup_step augmentation/Mixup.py unverified Apache-2.0 (permissive) · cc3a82b123fab81e · report
pixel_search perturb.py unverified Apache-2.0 (permissive) · 7c22627ec0aafc3a · report
step in 32 papers training.py unverified Apache-2.0 (permissive) · 6613eec4ec10b472 · report

Tasks

Data Augmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

RandAugment

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