Papers › New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and...

New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes

16 Oct 2024arXiv:2410.12671archive 2025-07-28

Yanyun Wang, Li Liu, Zi Liang, Qingqing Ye, Haibo Hu

Adversarial Training (AT) is one of the most effective methods to enhance the robustness of DNNs. However, existing AT methods suffer from an inherent trade-off between adversarial robustness and clean accuracy, which seriously hinders their real-world deployment. While this problem has been widely studied within the current AT paradigm, existing AT methods still typically experience a reduction in clean accuracy by over 10% to date, without significant improvements in robustness compared with simple baselines like PGD-AT. This inherent trade-off raises a question: whether the current AT paradigm, which assumes to learn the corresponding benign and adversarial samples as the same class, inappropriately combines clean and robust objectives that may be essentially inconsistent. In this work, we surprisingly reveal that up to 40% of CIFAR-10 adversarial samples always fail to satisfy such an assumption across various AT methods and robust models, explicitly indicating the improvement room for the current AT paradigm. Accordingly, to relax the tension between clean and robust learning derived from this overstrict assumption, we propose a new AT paradigm by introducing an additional dummy class for each original class, aiming to accommodate the hard adversarial samples with shifted distribution after perturbation. The robustness w.r.t. these adversarial samples can be achieved by runtime recovery from the predicted dummy classes to their corresponding original ones, eliminating the compromise with clean learning. Building on this new paradigm, we propose a novel plug-and-play AT technology named DUmmy Classes-based Adversarial Training (DUCAT). Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that the DUCAT concurrently improves clean accuracy and adversarial robustness compared with state-of-the-art benchmarks, effectively breaking the existing inherent trade-off.

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 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 8 ran (6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

FlaAI/DUCAT officialmentioned in paperpytorchSyntology: 11 samples, 8 ran (2 instrument-failed) · 3 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

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 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.

2ran · our draft was wrong
6ran
3unverified

Licence: 11 of the 11 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 FlaAI/DUCAT. “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.

FlaAI/DUCAT official repository 11 samples, 8 ran (2 instrument-failed) · 3 unverified
conv3x3 in 1,376 papers models/resnet.py ran · our draft was wrong no licence file found · 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
generate_trades adv_lib/trades.py ran no licence file found · pointer only · ac1f9f2db28ed472 · report fixture: signature model:callable/0/?, x_natural:Tensor/2/float, distance:str/0/str, eps:float/0/float, eps_iter:float/0/float, nb_iter:int/0/int, clip_min:float/0/float, clip_max:float/0/float · returned Tensor · level recorded 2026-09-24
get_optimizer in 228 papers common/utils.py ran no licence file found · pointer only · 862109fd2598e9de · report fixture: signature P:Config/0/?, model:callable/0/? · returned tuple · level recorded 2026-09-24
get_scheduler in 122 papers common/utils.py ran no licence file found · pointer only · 700a41318238fb05 · report fixture: signature P:Config/0/?, optimizer:SGD/0/?, lr_decay_gamma:float/0/float · returned CosineAnnealingLR · level recorded 2026-09-24
kl_div in 22 papers
census: 6 implementations from 6 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
adv_lib/trades.py ran no licence file found · pointer only · 5e25bba79f6b2977 · report fixture: signature input:Tensor/2/float, targets:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-24
mart_loss adv_lib/mart.py ran · our draft was wrong no licence file found · pointer only · 06b924f8eaabec1c · report fixture: returned tuple · level recorded 2026-09-22
mart_loss_dummy adv_lib/mart.py ran no licence file found · pointer only · f205deb59250d5ba · report fixture: signature P:ConfigP/0/?, model:callable/0/?, x_natural:Tensor/4/float, y:Tensor/1/int, optimizer:SGD/0/?, eps_iter:float/0/float, eps:float/0/float, nb_iter:int/0/int, beta:float/0/float, clip_min:float/0/float, clip_max:float/0/float, distance:str/0/str, return_adv:bool/0/bool, return_adv_sample:bool/0/bool · returned tuple · level recorded 2026-09-24
trades_loss in 11 papers adv_lib/trades.py ran no licence file found · pointer only · 67940ec0772eb65d · report fixture: signature model:callable/0/?, x_natural:Tensor/2/float, y:Tensor/1/int, distance:str/0/str, eps_iter:float/0/float, eps:float/0/float, nb_iter:int/0/int, beta:float/0/float, clip_min:float/0/float, clip_max:float/0/float · returned tuple · level recorded 2026-09-24
get_CIFAR100_C datasets/cifar_c.py unverified no licence file found · pointer only · f219a9828f30f13e · report
get_CIFAR10_C datasets/cifar_c.py unverified no licence file found · pointer only · 512759d1e2dba1bb · report
parse_args in 355 papers common/common.py unverified no licence file found · pointer only · b88315b579fdf1c6 · report

Tasks

Adversarial Robustness

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