SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.12508 · ICML · 2022

Adversarial Robustness against Multiple and Single l p -Threat Models via Quick Fine-Tuning of Robust Classifiers

Matthias Hein, Francesco Croce

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 0 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/2105.12508.json · badge: /api/ran/2105.12508.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
fra31/robust-finetuning canonical (classifier label)
classifier basis: classifier_2025
7 ran · 0 no recorded run
FunctionStatusWhere it lives
L0_norm Ran
ran, honoured the contract we drafted
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("a1b32de808e46be1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

L1_projection Ran
ran; our contract draft was wrong, not the code
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("f0f026ce0c0e2f39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

L2_norm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("fa19820305aabe1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

apgd_train Ran
ran; our contract draft was wrong, not the code
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("1c1759c14ebe4efe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

check_oscillation Ran
ran; our contract draft was wrong, not the code
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("1b13d7d6e5549507")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

dlr_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("278b4e6a4d60be18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

dlr_loss_targeted Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fra31/robust-finetuning/autopgd_train.py
pointer only (licence: NONE) · get_code("d9464e6ee7eb0c8f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fra31/robust-finetuning 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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 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
L1_projection
brick of this paper's assembly: helper
8 other papers
3 dated earlier, 5 later · 2 only as an assembly brick
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
2103.01208 (2021-03)
Mind the Box: l 1 -APGD for Sparse Adversarial Attacks on Image Classifiers
2103.14222 (2021-03)
Adversarial Attacks are Reversible with Natural Supervision
and 5 more not named here
L2_norm
brick of this paper's assembly: helper
5 other papers
1 dated earlier, 4 later · 4 only as an assembly brick
2103.01208 (2021-03)
Mind the Box: l 1 -APGD for Sparse Adversarial Attacks on Image Classifiers
2311.16124 (2023-11)
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
2312.01260 (2023-12)
Rethinking PGD Attack: Is Sign Function Necessary?
and 2 more not named here
L0_norm
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 3 only as an assembly brick
2103.01208 (2021-03)
Mind the Box: l 1 -APGD for Sparse Adversarial Attacks on Image Classifiers
2402.12336 (2024-02)
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
2506.03355 (2025-06)
Robustness in Both Domains: CLIP Needs a Robust Text Encoder
check_oscillation
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2402.12336 (2024-02)
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
2506.03355 (2025-06)
Robustness in Both Domains: CLIP Needs a Robust Text Encoder

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

A major drawback of adversarially robust models, in particular for large scale datasets like Im-ageNet, is the extremely long training time compared to standard ones. Moreover, models should be robust not only to one l p -threat model but ideally to all of them. In this paper we propose Extreme norm Adversarial Training (E-AT) for multiple-norm robustness which is based on geometric properties of l p -balls. E-AT costs up to three times less than other adversarial training methods for multiple-norm robustness. Using E-AT we show that for ImageNet a single epoch and for CIFAR-10 three epochs are sufficient to turn any l p -robust model into a multiplenorm robust model. In this way we get the first multiple-norm robust model for ImageNet and boost the state-of-the-art for multiple-norm robustness to more than 51% on CIFAR-10. Finally, we study the general transfer via finetuning of adversarial robustness between different individual l p -threat models and improve the previous SOTA l 1 -robustness on both CIFAR-10 and ImageNet. Extensive experiments show that our scheme works across datasets and architectures including vision transformers.

For agents

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

get_harvested_code_for_paper("2105.12508")
get_code_for_paper("2105.12508")
have("2105.12508")

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

curl https://syntology.ai/api/ran/2105.12508.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.12508.svg)](https://syntology.ai/paper/2105.12508)

Connect an agent — have() is free.