Papers › Theoretically Principled Trade-off between Robustness and Accuracy

Theoretically Principled Trade-off between Robustness and Accuracy

24 Jan 2019arXiv:1901.08573archive 2025-07-28

Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael. I. Jordan

We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning the theory underlying this trade-off. In this work, we decompose the prediction error for adversarial examples (robust error) as the sum of the natural (classification) error and boundary error, and provide a differentiable upper bound using the theory of classification-calibrated loss, which is shown to be the tightest possible upper bound uniform over all probability distributions and measurable predictors. Inspired by our theoretical analysis, we also design a new defense method, TRADES, to trade adversarial robustness off against accuracy. Our proposed algorithm performs well experimentally in real-world datasets. The methodology is the foundation of our entry to the NeurIPS 2018 Adversarial Vision Challenge in which we won the 1st place out of ~2,000 submissions, surpassing the runner-up approach by 11.41% in terms of mean ℓ₂ perturbation distance.

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 15 code samples harvested from 7 repositories linked to this paper: 12 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 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: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 14 samples from 6 repositories, 11 ran (7 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

yaodongyu/TRADES officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
TonyYaoMSU/TRADES mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
arobey1/advbench mentioned on GitHubpytorchSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified report
goldblum/AdversariallyRobustDistillation mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adversarially Robust Distillation (arXiv:1905.09747; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nutellamok/advrush mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
optimization-for-data-driven-science/dair mentioned on GitHubpytorchSyntology: not harvested report
val-iisc/flss mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zjfheart/Friendly-Adversarial-Training mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
salomonhotegni/MOREL pytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 12 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 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.

4ran · our draft was wrong
1ran; the contract check could not run
7ran
3unverified

Licence: 4 of the 15 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 7 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

yaodongyu/TRADES official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
trades_loss in 11 papers trades.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 · 0dbf499b0160d7e3 · report fixture: returned Tensor · level recorded, date not recorded
TonyYaoMSU/TRADES community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
trades_loss in 11 papers TRADES-master/trades.py ran · our draft was wrong no licence file found · pointer only · 4f4e01ae4a9aeecf · report fixture: signature model:callable/0/?, x_natural:Tensor/4/float, y:Tensor/1/int, optimizer:SGD/0/?, step_size:float/0/float, epsilon:float/0/float, perturb_steps:int/0/int, beta:float/0/float, distance:str/0/str · returned Tensor · level recorded 2026-09-22
arobey1/advbench community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
Attack in 15 papers advbench/algorithms.py ran MIT (permissive) · bca439beb127432f · report fixture: returned Attack · level recorded 2026-09-22
Attack_Linf advbench/algorithms.py ran MIT (permissive) · 808053223b371f29 · report fixture: returned Attack_Linf · level recorded 2026-09-22
AverageMeter in 26 papers advbench/algorithms.py ran MIT (permissive) · 61308ee90996cb91 · report fixture: returned AverageMeter · level recorded 2026-09-22
Classifier in 72 papers advbench/algorithms.py ran; the contract check could not run (RAISES) MIT (permissive) · 95d7d9e951192fbe · report fixture: signature input_shape:tuple/1/int, num_classes:int/0/int, hparams:dict/0/? · returned MNISTNet · level recorded 2026-09-22
MNISTNet advbench/algorithms.py ran MIT (permissive) · cc62770b8a2f07cb · report fixture: returned MNISTNet · level recorded 2026-09-22
ResNet18 in 174 papers advbench/algorithms.py ran MIT (permissive) · 35e1414137593b9e · report fixture: returned ResNet · level recorded 2026-09-22
TRADES_Linf advbench/algorithms.py ran fingerprinted MIT (permissive) · 4cce9cc92ffa9b07 · report fixture: returned TRADES_Linf · level recorded 2026-09-22
Algorithm in 26 papers advbench/algorithms.py unverified MIT (permissive) · afdbbd69eb450e7d · report
TRADES advbench/algorithms.py unverified MIT (permissive) · 8af50e8650fba9a4 · report
nutellamok/advrush community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
trades_loss in 11 papers advrush/trades.py ran · our draft was wrong Apache-2.0 (permissive) · ae05ac36b5660867 · report fixture: returned Tensor · level recorded 2026-09-22
val-iisc/flss community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
TradesAWP CIFAR10/Train/utils_awp.py ran no licence file found · pointer only · c1b3357620672711 · report fixture: returned TradesAWP · level recorded 2026-09-22
zjfheart/Friendly-Adversarial-Training community (archive-listed) 1 sample, 0 ran · 1 unverified
TRADES_loss FAT_for_TRADES.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 310d3d6ec0329c05 · report
salomonhotegni/MOREL community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
trades_loss in 11 papers src/advermorel/losses/trades.py ran · our draft was wrong MIT (permissive) · e79913f3ab121c59 · report fixture: returned Tensor · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

7 sibling assemblies for TRADES (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for TRADES (graph method: TRADES). 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. trades_loss entry · level 1 · ran · our draft was wrong · 4f4e01ae4a9aeecf

harvested Assembly for TRADES (graph method: TRADES). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. TRADES_loss entry · level 0 · unverified · 310d3d6ec0329c05

harvested Assembly for TRADES (graph method: TRADES). 11 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. TRADES entry · level 0 · unverified · 8af50e8650fba9a4
  2. Algorithm helper · level 0 · unverified · afdbbd69eb450e7d
  3. AverageMeter helper · level 1 · ran · 61308ee90996cb91
  4. TRADES_Linf loss · level 1 · ran · 4cce9cc92ffa9b07
  5. Classifier helper · level 1 · ran; the contract check could not run (RAISES) · 95d7d9e951192fbe
  6. Attack_Linf helper · level 1 · ran · 808053223b371f29
  7. MNISTNet helper · level 1 · ran · cc62770b8a2f07cb
  8. ResNet18 helper · level 1 · ran · 35e1414137593b9e
  9. Attack helper · level 1 · ran · bca439beb127432f
  10. BasicBlock helper · level 1 · ran · e33f907725fe74f0
  11. ResNet helper · level 1 · ran · a0485d54af2ef2ac

harvested Assembly for TRADES (graph method: TRADES). 3 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. TradesAWP entry · level 1 · ran · c1b3357620672711
  2. add_into_weights helper · level 0 · unverified · c4d59bb1cb0ef29e
  3. diff_in_weights helper · level 1 · ran · our draft was wrong · 4170809219439d13

harvested Assembly for TRADES (graph method: TRADES). 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. trades_loss entry · level 1 · ran · our draft was wrong · 0dbf499b0160d7e3

harvested Assembly for TRADES (graph method: TRADES). 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. trades_loss entry · level 1 · ran · our draft was wrong · ae05ac36b5660867

harvested Assembly for TRADES (graph method: TRADES). 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. trades_loss entry · level 1 · ran · our draft was wrong · e79913f3ab121c59

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="1901.08573") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Adversarial AttackAdversarial DefenseAdversarial RobustnessGeneral Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Adversarial Attack CIFAR-10 TRADES [zhang2019b] Attack: PGD20 45.900 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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