SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.10045 · 2024

Towards Adversarially Robust Dataset Distillation by Curvature Regularization

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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, 1 violated it and 0 have no contract verdict; 14 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2403.10045.json · badge: /api/ran/2403.10045.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
yumozi/guard canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
clip_cifar Ran
ran; our contract draft was wrong, not the code
yumozi/guard/recover/recover_cifar.py
pointer only (licence: NONE) · get_code("d3ba0def38e62a16")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

compute_wasserstein_barycenter Ran
ran; our contract draft was wrong, not the code
yumozi/guard/recover/barycenter.py
pointer only (licence: NONE) · get_code("86f5a43a05aa1c9b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
yumozi/guard/models/resnet.py
pointer only (licence: NONE) · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
yumozi/guard/models/resnet.py
pointer only (licence: NONE) · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

denormalize_cifar Ran
ran; our contract draft was wrong, not the code
yumozi/guard/recover/recover_cifar.py
pointer only (licence: NONE) · get_code("47db86feca98203a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

fast_is_better_than_free Ran
ran; our contract draft was wrong, not the code
yumozi/guard/pretrain/pretrain.py
pointer only (licence: NONE) · get_code("89c3215b7bc92caf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

fixed_support_barycenter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yumozi/guard/recover/barycenter.py
pointer only (licence: NONE) · get_code("d80ff6e1df7cb876")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

get_image_size_map Ran
ran; our contract draft was wrong, not the code
yumozi/guard/pretrain/utils.py
pointer only (licence: NONE) · get_code("7a74def3fdadd855")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

get_module Ran
ran; our contract draft was wrong, not the code
yumozi/guard/pretrain/presets.py
pointer only (licence: NONE) · get_code("b2ea55703711dd12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

get_num_class_map Ran
ran; our contract draft was wrong, not the code
yumozi/guard/pretrain/utils.py
pointer only (licence: NONE) · get_code("338cd6960a213cdb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

prepare_data Ran
ran; our contract draft was wrong, not the code
yumozi/guard/recover/data_synthesis.py
pointer only (licence: NONE) · get_code("4780f5edc4e40df5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

project_simplex Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yumozi/guard/recover/barycenter.py
pointer only (licence: NONE) · get_code("3cbc04eada4612a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

str2bool Ran
ran, violated the contract we drafted
yumozi/guard/pretrain/utils.py
pointer only (licence: NONE) · get_code("7c508037b40522af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

trades_attack Ran
ran; our contract draft was wrong, not the code
yumozi/guard/pretrain/pretrain.py
pointer only (licence: NONE) · get_code("57ebedfddf9562e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

trades_loss Ran
ran; our contract draft was wrong, not the code
yumozi/guard/pretrain/pretrain.py
pointer only (licence: NONE) · get_code("29ca9d1819cac58b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

resnet18 Not yet run
unverified (harvested, no recorded run)
yumozi/guard/models/resnet.py
pointer only (licence: NONE) · get_code("8874836603a819db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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.

validate Not yet run
unverified (harvested, no recorded run)
yumozi/guard/recover/data_synthesis.py
pointer only (licence: NONE); the stored copy get_code serves, from VILA-Lab/SRe2L, is pointer only (licence: NONE) · get_code("230fb2e9963063c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yumozi/guard when it was checked. 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 5 later) and 12 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
conv1x1 431 other papers
330 dated earlier, 13 the same month, 77 later, 10 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
226 dated earlier, 11 the same month, 64 later, 10 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
str2bool 175 other papers
113 dated earlier, 4 the same month, 57 later, 1 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
validate 7 other papers
3 dated earlier, 4 later
2306.13092 (2023-06)
Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
2311.17950 (2023-11)
Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
2312.03526 (2023-12)
On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
and 4 more not named here
get_module 2 other papers
2 later
2406.10485 (2024-06)
A Label is Worth a Thousand Images in Dataset Distillation
2411.02853 (2024-11)
ADOPT: Modified Adam Can Converge with Any β 2 with the Optimal Rate

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 2026-11-22.

Repositories linked to this paper

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

Abstract

Dataset distillation (DD) allows datasets to be distilled to fractions of their original size while preserving the rich distributional information, so that models trained on the distilled datasets can achieve a comparable accuracy while saving significant computational loads. Recent research in this area has been focusing on improving the accuracy of models trained on distilled datasets. In this paper, we aim to explore a new perspective of DD. We study how to embed adversarial robustness in distilled datasets, so that models trained on these datasets maintain the high accuracy and meanwhile acquire better adversarial robustness. We propose a new method that achieves this goal by incorporating curvature regularization into the distillation process with much less computational overhead than standard adversarial training. Extensive empirical experiments suggest that our method not only outperforms standard adversarial training on both accuracy and robustness with less computation overhead but is also capable of generating robust distilled datasets that can withstand various adversarial attacks. Our implementation is available at: https://github.com/yumozi/GUARD.

For agents

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

get_harvested_code_for_paper("2403.10045")
get_code_for_paper("2403.10045")
have("2403.10045")

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

curl https://syntology.ai/api/ran/2403.10045.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.10045.svg)](https://syntology.ai/paper/2403.10045)

Connect an agent — have() is free.