SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.12443 · ECCV · 2024

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective

Yaochu Jin, Handing Wang, Cong Tian, Zhaoxin Wang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 5 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; 4 no recorded run), measured 2026-11-22; 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/2407.12443.json · badge: /api/ran/2407.12443.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
HandingWangXDGroup/FGSM-PCO community
Papers with Code archive
1 ran · 4 no recorded run
FunctionStatusWhere it lives
atta_aug Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HandingWangXDGroup/FGSM-PCO/FGSM-PCO.py
pointer only (licence: NONE) · get_code("eda67bbf007849b8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HandingWangXDGroup/FGSM-PCO 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.

LabelSmoothLoss Not yet run
unverified (harvested, no recorded run)
HandingWangXDGroup/FGSM-PCO/FGSM-PCO.py
pointer only (licence: NONE) · get_code("abd0cd6b28aa41cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HandingWangXDGroup/FGSM-PCO 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.

_label_smoothing Not yet run
unverified (harvested, no recorded run)
HandingWangXDGroup/FGSM-PCO/FGSM-PCO.py
pointer only (licence: NONE) · get_code("c151b506126b02e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HandingWangXDGroup/FGSM-PCO 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_args Not yet run
unverified (harvested, no recorded run)
HandingWangXDGroup/FGSM-PCO/FGSM-PCO.py
pointer only (licence: NONE) · get_code("b3fae58feea5a38b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HandingWangXDGroup/FGSM-PCO 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.

main Not yet run
unverified (harvested, no recorded run)
HandingWangXDGroup/FGSM-PCO/FGSM-PCO.py
pointer only (licence: NONE) · get_code("9bf5d16916540519")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HandingWangXDGroup/FGSM-PCO 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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, 1 later) and 3 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
LabelSmoothLoss
brick of this paper's assembly: loss
3 other papers
2 dated earlier, 1 later
2207.08859 (2022-07)
Prior-Guided Adversarial Initialization for Fast Adversarial Training
2308.12857 (2023-08)
Fast Adversarial Training with Smooth Convergence
atta_aug
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.08034 (2020-10)
Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training

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

Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT methods, fast AT (FAT), which employs a single-step attack strategy to guide the training process, can achieve good robustness against adversarial attacks at a low cost. However, FAT methods suffer from the catastrophic overfitting problem, especially on complex tasks or with large-parameter models. In this work, we propose a FAT method termed FGSM-PCO, which mitigates catastrophic overfitting by averting the collapse of the inner optimization problem in the bi-level optimization process. FGSM-PCO generates current-stage AEs from the historical AEs and incorporates them into the training process using an adaptive mechanism. This mechanism determines an appropriate fusion ratio according to the performance of the AEs on the training model. Coupled with a loss function tailored to the training framework, FGSM-PCO can alleviate catastrophic overfitting and help the recovery of an overfitted model to effective training. We evaluate our algorithm across three models and three datasets to validate its effectiveness. Comparative empirical studies against other FAT algorithms demonstrate that our proposed method effectively addresses unresolved overfitting issues in existing algorithms.

For agents

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

get_harvested_code_for_paper("2407.12443")
get_code_for_paper("2407.12443")
have("2407.12443")

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

curl https://syntology.ai/api/ran/2407.12443.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.12443.svg)](https://syntology.ai/paper/2407.12443)

Connect an agent — have() is free.