Papers › DAFA: Distance-Aware Fair Adversarial Training

DAFA: Distance-Aware Fair Adversarial Training

23 Jan 2024arXiv:2401.12532archive 2025-07-28

Hyungyu Lee, Saehyung Lee, Hyemi Jang, Junsung Park, Ho Bae, Sungroh Yoon

The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem. Existing methodologies aimed to enhance robust fairness by sacrificing the model's performance on easier classes in order to improve its performance on harder ones. However, we observe that under adversarial attacks, the majority of the model's predictions for samples from the worst class are biased towards classes similar to the worst class, rather than towards the easy classes. Through theoretical and empirical analysis, we demonstrate that robust fairness deteriorates as the distance between classes decreases. Motivated by these insights, we introduce the Distance-Aware Fair Adversarial training (DAFA) methodology, which addresses robust fairness by taking into account the similarities between classes. Specifically, our method assigns distinct loss weights and adversarial margins to each class and adjusts them to encourage a trade-off in robustness among similar classes. Experimental results across various datasets demonstrate that our method not only maintains average robust accuracy but also significantly improves the worst robust accuracy, indicating a marked improvement in robust fairness compared to existing methods.

PaperPDFCodeCode Syntology ranMethod as code

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 17 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed); found in paper text by Syntology: 9 samples from 1 repository, 6 ran (0 with no instrument failure; 6 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.

rucy74/DAFA officialmentioned in paperpytorchSyntology: 8 samples, 5 ran (3 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

17 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 6 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.

7ran · our draft was wrong
2ran; the contract check could not run
2ran
6unverified

Licence: 17 of the 17 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 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.

rucy74/DAFA official repository 8 samples, 5 ran (3 instrument-failed) · 3 unverified
PreActResNet18 in 38 papers models/preact_resnet.py ran · our draft was wrong no licence file found · pointer only · 1153837ba4a94242 · report fixture: signature num_classes:int/0/int · returned PreActResNet · level recorded 2026-09-24
ResNet18 in 174 papers models/resnet.py ran · our draft was wrong no licence file found · pointer only · 0f23e7e681845fe0 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
eval in 90 papers evaluation.py ran no licence file found · pointer only · 18c82523ac3f528b · report fixture: signature args:Args/0/?, model:callable/0/?, device:device/0/?, eval_set:str/0/str, loader:list/1/tuple · returned dict · level recorded 2026-09-24
get_transform in 75 papers datasets.py ran · our draft was wrong no licence file found · pointer only · 240892d4d66578d4 · report fixture: signature dataset:str/0/str, train:bool/0/bool · returned Compose · level recorded 2026-09-24
pgd in 18 papers evaluation.py ran no licence file found · pointer only · b1ca971f9ac6b177 · report fixture: signature model:callable/0/?, X:Tensor/2/float, y:Tensor/1/int, epsilon:float/0/float, num_steps:int/0/int, step_size:float/0/float · returned tuple · level recorded 2026-09-24
calculate_class_weights utils.py unverified no licence file found · pointer only · 3dd1861dafcd1315 · report
madry_loss losses.py unverified no licence file found · pointer only · f25e91962b599eaf · report
trades_loss in 11 papers losses.py unverified no licence file found · pointer only · 72b23386d15d731a · report
hannxu123/fair_robust found in paper text by Syntology 9 samples, 6 ran (6 instrument-failed) · 3 unverified
cost_sensitive utils_frl.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fa59447ea22b5b18 · report fixture: signature lam0:Tensor/1/float, lam1:Tensor/1/float, lam2:Tensor/1/float · returned tuple · level recorded 2026-09-22
in_class utils_frl.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) · metamorphic tier: invariant licence of this copy not recorded · 0504a54e17169d2e · report fixture: signature predict:Tensor/1/int, label:Tensor/1/int · returned Tensor · level recorded 2026-09-22
match_weight utils_frl.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 9fc4a65d0199cf9c · report fixture: signature label:Tensor/1/int, diff0:list/1/Tensor, diff1:list/1/Tensor, diff2:list/1/Tensor · returned tuple · level recorded 2026-09-22
normalize_lambda utils_frl.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 4bbdb8c0c8ea6043 · report fixture: signature lmb:Tensor/1/float, lim:float/0/float · returned Tensor · level recorded 2026-09-22
pgd_attack in 10 papers utils_frl.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 · our draft was wrong licence of this copy not recorded · ee1e48fc088d1214 · report fixture: signature model:callable/0/?, X:Tensor/4/float, y:Tensor/1/int, epsilon:float/0/float, clip_max:float/0/float, clip_min:float/0/float, num_steps:int/0/int, step_size:float/0/float · returned Tensor · level recorded 2026-09-22
trades_adv utils_frl.py ran · our draft was wrong no licence file found · pointer only · eca04e0dead8a043 · report fixture: signature model:callable/0/?, x_natural:Tensor/2/float, weight:Tensor/1/float, epsilon:float/0/float, clip_max:float/0/float, clip_min:float/0/float, num_steps:int/0/int, step_size:float/0/float · returned Tensor · level recorded 2026-09-24
evaluate in 514 papers utils_frl.py unverified no licence file found · pointer only · 4cf5ffbe5a5795e2 · report
frl_train utils_frl.py unverified no licence file found · pointer only · ae909bf23603872c · report
train_model in 103 papers utils_frl.py unverified no licence file found · pointer only · d986a04b9eef9dcc · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DAFA (graph method: DAFA). 9 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. frl_train entry · level 0 · unverified · ae909bf23603872c
  2. cost_sensitive loss · level 1 · ran · our draft was wrong · fa59447ea22b5b18
  3. evaluate metric · level 0 · unverified · 4cf5ffbe5a5795e2
  4. normalize_lambda helper · level 1 · ran · our draft was wrong · 4bbdb8c0c8ea6043
  5. train_model helper · level 0 · unverified · d986a04b9eef9dcc
  6. in_class helper · level 1 · ran; the contract check could not run (RAISES) · 0504a54e17169d2e
  7. pgd_attack helper · level 1 · ran · our draft was wrong · ee1e48fc088d1214
  8. match_weight helper · level 1 · ran; the contract check could not run (RAISES) · 9fc4a65d0199cf9c
  9. trades_adv helper · level 1 · ran · our draft was wrong · eca04e0dead8a043

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2401.12532") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Fairness

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