SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.16352 · 2024

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

arXiv · PDF · Open in the Atlas

Code that ran

14 of 18 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 4 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/2401.16352.json · badge: /api/ran/2401.16352.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
glin2022/atop canonical (classifier label)
classifier basis: census
14 ran · 4 no recorded run
FunctionStatusWhere it lives
adv_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
glin2022/atop/torchattacks_local/stadv.py
pointer only (licence: NONE) · get_code("101946f394ff2d40")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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_color Ran
ran, honoured the contract we drafted
glin2022/atop/model/networks.py
pointer only (licence: NONE) · get_code("fb78a77b5eb800b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

downsample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
glin2022/atop/classifiers/attribute_classifier.py
pointer only (licence: NONE) · get_code("a56784666af5bd6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

flow_loss Ran
ran; our contract draft was wrong, not the code
glin2022/atop/torchattacks_local/stadv.py
pointer only (licence: NONE) · get_code("1704d0e302cf4139")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

flow_to_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
glin2022/atop/model/networks.py
pointer only (licence: NONE) · get_code("e82ba5f570765085")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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_logit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
glin2022/atop/classifiers/attribute_classifier.py
pointer only (licence: NONE) · get_code("a59556109795f95c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

hinge_loss_d Ran
ran; our contract draft was wrong, not the code
glin2022/atop/model/losses.py
pointer only (licence: NONE) · get_code("137ebcbb6c6379a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

is_image_file Ran
ran, violated the contract we drafted
glin2022/atop/utils/data.py
pointer only (licence: NONE) · get_code("1fabc732ffcd8750")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

lerp_clip Ran
ran; our contract draft was wrong, not the code
glin2022/atop/classifiers/attribute_net.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("195d635db8eb778b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

ls_loss_d Ran
ran; our contract draft was wrong, not the code
glin2022/atop/model/losses.py
pointer only (licence: NONE) · get_code("e18af9981db25101")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

ls_loss_g Ran
ran; our contract draft was wrong, not the code
glin2022/atop/model/losses.py
pointer only (licence: NONE) · get_code("24947afc30d8acc3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

max_res_from_state_dict Ran
ran, honoured the contract we drafted
glin2022/atop/classifiers/attribute_net.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("d5eb57879ef1704e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

pil_loader Ran
ran, honoured the contract we drafted
glin2022/atop/utils/data.py
pointer only (licence: NONE) · get_code("f321f54723433661")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

wrapper_method Ran
ran; our contract draft was wrong, not the code
glin2022/atop/torchattacks_local/attack.py
pointer only (licence: NONE); the stored copy get_code serves, from nilspwalter/the-uncanny-valley, is pointer only (licence: NOASSERTION) · get_code("9b45cb80d93fe980")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

flow_st Not yet run
unverified (harvested, no recorded run)
glin2022/atop/torchattacks_local/stadv.py
pointer only (licence: NONE) · get_code("1beef8065a504d20")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

from_state_dict Not yet run
unverified (harvested, no recorded run)
glin2022/atop/classifiers/attribute_net.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("0dd156dfa78cac88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

get_softmaxed Not yet run
unverified (harvested, no recorded run)
glin2022/atop/classifiers/attribute_classifier.py
pointer only (licence: NONE) · get_code("6a3bd6aafe71b50e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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.

output_to_image Not yet run
unverified (harvested, no recorded run)
glin2022/atop/model/networks.py
pointer only (licence: NONE) · get_code("0303f947b7d3c5d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, glin2022/atop 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 5 later) and 10 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
pil_loader 66 other papers
43 dated earlier, 21 later, 2 same year, order not determinable
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
and 63 more not named here
wrapper_method 6 other papers
1 dated earlier, 5 later
2310.18274 (2023-10)
LipSim: A Provably Robust Perceptual Similarity Metric
2402.02309 (2024-02)
Jailbreaking Attack against Multimodal Large Language Model
2405.16918 (2024-05)
The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective
and 3 more not named here
lerp_clip 3 other papers
2 dated earlier, 1 later
2205.07460 (2022-05)
Diffusion Models for Adversarial Purification
2311.16124 (2023-11)
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
2408.08502 (2024-08)
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
max_res_from_state_dict 3 other papers
2 dated earlier, 1 later
2205.07460 (2022-05)
Diffusion Models for Adversarial Purification
2311.16124 (2023-11)
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
2408.08502 (2024-08)
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
downsample 2 other papers
2 dated earlier
2205.07460 (2022-05)
Diffusion Models for Adversarial Purification
2311.18403 (2023-11)
Detecting and Corrupting Convolution-based Unlearnable Examples
from_state_dict 2 other papers
1 dated earlier, 1 later
2311.16124 (2023-11)
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
2408.08502 (2024-08)
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
get_logit 2 other papers
2 dated earlier
2205.07460 (2022-05)
Diffusion Models for Adversarial Purification
2311.18403 (2023-11)
Detecting and Corrupting Convolution-based Unlearnable Examples
get_softmaxed 1 other paper
1 dated earlier
2311.18403 (2023-11)
Detecting and Corrupting Convolution-based Unlearnable Examples

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

The deep neural networks are known to be vulnerable to well-designed adversarial attacks. The most successful defense technique based on adversarial training (AT) can achieve optimal robustness against particular attacks but cannot generalize well to unseen attacks. Another effective defense technique based on adversarial purification (AP) can enhance generalization but cannot achieve optimal robustness. Meanwhile, both methods share one common limitation on the degraded standard accuracy. To mitigate these issues, we propose a novel pipeline to acquire the robust purifier model, named Adversarial Training on Purification (AToP), which comprises two components: perturbation destruction by random transforms (RT) and purifier model fine-tuned (FT) by adversarial loss. RT is essential to avoid overlearning to known attacks, resulting in the robustness generalization to unseen attacks, and FT is essential for the improvement of robustness. To evaluate our method in an efficient and scalable way, we conduct extensive experiments on CIFAR-10, CIFAR-100, and ImageNette to demonstrate that our method achieves optimal robustness and exhibits generalization ability against unseen attacks.

For agents

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

get_harvested_code_for_paper("2401.16352")
get_code_for_paper("2401.16352")
have("2401.16352")

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

curl https://syntology.ai/api/ran/2401.16352.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.16352.svg)](https://syntology.ai/paper/2401.16352)

Connect an agent — have() is free.