Papers › Data Augmentation Alone Can Improve Adversarial Training

Data Augmentation Alone Can Improve Adversarial Training

24 Jan 2023arXiv:2301.09879archive 2025-07-28

Lin Li, Michael Spratling

Adversarial training suffers from the issue of robust overfitting, which seriously impairs its generalization performance. Data augmentation, which is effective at preventing overfitting in standard training, has been observed by many previous works to be ineffective in mitigating overfitting in adversarial training. This work proves that, contrary to previous findings, data augmentation alone can significantly boost accuracy and robustness in adversarial training. We find that the hardness and the diversity of data augmentation are important factors in combating robust overfitting. In general, diversity can improve both accuracy and robustness, while hardness can boost robustness at the cost of accuracy within a certain limit and degrade them both over that limit. To mitigate robust overfitting, we first propose a new crop transformation, Cropshift, which has improved diversity compared to the conventional one (Padcrop). We then propose a new data augmentation scheme, based on Cropshift, with much improved diversity and well-balanced hardness. Empirically, our augmentation method achieves the state-of-the-art accuracy and robustness for data augmentations in adversarial training. Furthermore, when combined with weight averaging it matches, or even exceeds, the performance of the best contemporary regularization methods for alleviating robust overfitting. Code is available at: https://github.com/TreeLLi/DA-Alone-Improves-AT.

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: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (13 with no instrument failure; 1 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

treelli/da-alone-improves-at officialmentioned in paperpytorchMITSyntology: 15 samples, 14 ran (1 instrument-failed) · 1 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: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 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 · our draft was wrong
13ran
1unverified

Licence: 1 of the 15 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 treelli/da-alone-improves-at. “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.

treelli/da-alone-improves-at official repository 15 samples, 14 ran (1 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
src/utils/helper.py ran MIT (permissive) · 4fd5d1dd1a797d37 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
check_bn in 9 papers src/utils/swa.py ran MIT (permissive) · 37174e6f1756c905 · report fixture: signature model:callable/0/? · returned bool · level recorded 2026-09-25
complete_ids src/utils/log.py ran fingerprinted MIT (permissive) · 4e3bcb7fb6c461e4 · report fixture: signature ids:str/0/str · returned str · level recorded 2026-09-25
conv3x3 in 1,376 papers src/model/wide_resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 583f9780bdd00a45 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
gather_all src/utils/helper.py ran MIT (permissive) · e7976a487657389f · report fixture: signature rank:int/0/int, world_size:int/0/int, target:Tensor/2/float · returned list · level recorded 2026-09-25
ids_from_idx src/utils/log.py ran fingerprinted MIT (permissive) · eac0350365e31875 · report fixture: signature idx:int/0/int · returned str · level recorded 2026-09-25
idx_from_ids src/utils/log.py ran fingerprinted MIT (permissive) · c4060e502670b5cb · report fixture: signature ids:str/0/str · returned int · level recorded 2026-09-25
input_grad src/utils/adversary.py ran MIT (permissive) · b63f8dddc272ba67 · report fixture: signature imgs:Tensor/2/float, targets:Tensor/1/int, model:callable/0/?, criterion:callable/0/? · returned Tensor · level recorded 2026-09-25
perturb in 20 papers
census: 4 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
src/utils/adversary.py ran MIT (permissive) · c4ff8c6f13f39bc5 · report fixture: signature imgs:Tensor/2/float, targets:Tensor/1/int, model:callable/0/?, criterion:callable/0/?, eps:float/0/float, eps_step:float/0/float, pert:NoneType/0/?, ig:NoneType/0/? · returned tuple · level recorded 2026-09-25
pgd in 18 papers src/utils/adversary.py ran MIT (permissive) · e36d3bdff03face5 · report fixture: signature imgs:Tensor/2/float, targets:Tensor/1/int, model:callable/0/?, criterion:callable/0/?, eps:float/0/float, eps_step:float/0/float, max_iter:int/0/int, pert:NoneType/0/?, ig:NoneType/0/? · returned tuple · level recorded 2026-09-25
pixel_2_real src/config/config.py ran fingerprinted MIT (permissive) · 5d1ae0c45e71f173 · report fixture: signature pixel:int/0/int · returned float · level recorded 2026-09-26
real_2_pixel src/config/config.py ran fingerprinted MIT (permissive) · f33bd487ae731b24 · report fixture: signature real:float/0/float · returned int · level recorded 2026-09-26
upper src/config/config.py ran fingerprinted MIT (permissive) · c4a5928bd44f924c · report fixture: signature x:str/0/str · returned str · level recorded 2026-09-26
word src/utils/printer.py ran MIT (permissive) · d49988befbdccf83 · report fixture: signature k:str/0/str, v:float/0/float · returned str · level recorded 2026-09-25
reduce_all src/utils/helper.py unverified MIT (permissive) · 44448a225e87438a · report

Tasks

Data AugmentationDiversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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