SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.11569 · 2020

Overfitting in adversarially robust deep learning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2002.11569.json · badge: /api/ran/2002.11569.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
FunctionStatusWhere it lives
mixup_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from csdongxian/AWP
pointer only · get_code("b20f1357b1d8dbf8")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

clamp Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from csdongxian/AWP
pointer only · get_code("8a93e041134b597a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
clamp 33 other papers
2 dated earlier, 31 later · 1 only as an assembly brick
1706.06083 (2017-06)
Towards Deep Learning Models Resistant to Adversarial Attacks
2001.03994 (2020-01)
Fast is better than free: Revisiting adversarial training
2003.01690 (2020-03)
Reliable Evaluation of Adversarial Robustness with an Ensemble of Diverse Parameter-free Attacks
and 30 more not named here
mixup_data 7 other papers
1 dated earlier, 6 later
1706.06083 (2017-06)
Towards Deep Learning Models Resistant to Adversarial Attacks
2003.01690 (2020-03)
Reliable Evaluation of Adversarial Robustness with an Ensemble of Diverse Parameter-free Attacks
2004.05884 (2020-04)
Adversarial Weight Perturbation Helps Robust Generalization
and 4 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the generalization performance of the classifier. In this paper, we empirically study this phenomenon in the setting of adversarially trained deep networks, which are trained to minimize the loss under worst-case adversarial perturbations. We find that overfitting to the training set does in fact harm robust performance to a very large degree in adversarially robust training across multiple datasets (SVHN, CIFAR-10, CIFAR-100, and ImageNet) and perturbation models ($\ell_\infty$ and $\ell_2$). Based upon this observed effect, we show that the performance gains of virtually all recent algorithmic improvements upon adversarial training can be matched by simply using early stopping. We also show that effects such as the double descent curve do still occur in adversarially trained models, yet fail to explain the observed overfitting. Finally, we study several classical and modern deep learning remedies for overfitting, including regularization and data augmentation, and find that no approach in isolation improves significantly upon the gains achieved by early stopping. All code for reproducing the experiments as well as pretrained model weights and training logs can be found at https://github.com/locuslab/robust_overfitting.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.11569")
get_code_for_paper("2002.11569")
have("2002.11569")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2002.11569.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2002.11569.svg)](https://syntology.ai/paper/2002.11569)

Connect an agent — have() is free.