SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.01260 · 2023

Rethinking PGD Attack: Is Sign Function Necessary?

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 9 failures of our instrument; 1 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/2312.01260.json · badge: /api/ran/2312.01260.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
junjieyang97/rgd canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
L1_norm Ran
ran; our contract draft was wrong, not the code
junjieyang97/rgd/autoattack/other_utils.py
pointer only (licence: LGPL-3.0) · get_code("edab3f9c146ad457")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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
junjieyang97/rgd/autoattack/autopgd_base.py
pointer only (licence: LGPL-3.0) · get_code("7325c49fd8c6a7d2")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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)
junjieyang97/rgd/autoattack/other_utils.py
pointer only (licence: LGPL-3.0); the stored copy get_code serves, from fra31/robust-finetuning, is pointer only (licence: NONE) · get_code("fa19820305aabe1d")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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_imgs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
junjieyang97/rgd/autoattack/other_utils.py
pointer only (licence: LGPL-3.0) · get_code("77fd60953273db9a")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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_range_output Ran
ran; our contract draft was wrong, not the code
junjieyang97/rgd/autoattack/checks.py
pointer only (licence: LGPL-3.0) · get_code("5d7ff050610414d0")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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_cifar10_test_loader Ran
ran; our contract draft was wrong, not the code
junjieyang97/rgd/attack.py
pointer only (licence: LGPL-3.0) · get_code("f73ae9cbfd1838f6")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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.

projection_l1 Ran
ran; our contract draft was wrong, not the code
junjieyang97/rgd/autoattack/fab_projections.py
pointer only (licence: LGPL-3.0) · get_code("9647e1400ee744e4")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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.

projection_l2 Ran
ran; our contract draft was wrong, not the code
junjieyang97/rgd/autoattack/fab_projections.py
pointer only (licence: LGPL-3.0) · get_code("a345677b413ef5ca")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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.

projection_linf Ran
ran; our contract draft was wrong, not the code
junjieyang97/rgd/autoattack/fab_projections.py
pointer only (licence: LGPL-3.0) · get_code("b8bdb6e496b4b5fa")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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_cifar100_test_loader Not yet run
unverified (harvested, no recorded run)
junjieyang97/rgd/attack.py
pointer only (licence: LGPL-3.0) · get_code("2d5dc7a04c57cafa")
How it ran

The body of this sample is withheld: LGPL-3.0, as GitHub detects it on this paper's repository, junjieyang97/rgd, is not in the permissive set Syntology serves inline. 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 2 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 8 other papers
6 dated earlier, 2 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 5 other papers
3 dated earlier, 2 later · 4 only as an assembly brick
2103.01208 (2021-03)
Mind the Box: l 1 -APGD for Sparse Adversarial Attacks on Image Classifiers
2105.12508 (2021-05)
Adversarial Robustness against Multiple and Single l p -Threat Models via Quick Fine-Tuning of Robust Classifiers
2311.16124 (2023-11)
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
and 2 more not named here
projection_l1 4 other papers
4 dated earlier
2006.13726 (2020-06)
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
2010.01950 (2020-10)
Torchattacks: A PyTorch Repository for Adversarial Attacks
2103.14222 (2021-03)
Adversarial Attacks are Reversible with Natural Supervision
and 1 more not named here
projection_l2 4 other papers
4 dated earlier
2006.13726 (2020-06)
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
2010.01950 (2020-10)
Torchattacks: A PyTorch Repository for Adversarial Attacks
2103.14222 (2021-03)
Adversarial Attacks are Reversible with Natural Supervision
and 1 more not named here
projection_linf 4 other papers
4 dated earlier
2006.13726 (2020-06)
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
2010.01950 (2020-10)
Torchattacks: A PyTorch Repository for Adversarial Attacks
2103.14222 (2021-03)
Adversarial Attacks are Reversible with Natural Supervision
and 1 more not named here
L1_norm 1 other paper
1 dated earlier
2103.01208 (2021-03)
Mind the Box: l 1 -APGD for Sparse Adversarial Attacks on Image Classifiers
check_range_output 1 other paper
1 dated earlier
2308.06703 (2023-08)
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

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

Neural networks have demonstrated success in various domains, yet their performance can be significantly degraded by even a small input perturbation. Consequently, the construction of such perturbations, known as adversarial attacks, has gained significant attention, many of which fall within "white-box" scenarios where we have full access to the neural network. Existing attack algorithms, such as the projected gradient descent (PGD), commonly take the sign function on the raw gradient before updating adversarial inputs, thereby neglecting gradient magnitude information. In this paper, we present a theoretical analysis of how such sign-based update algorithm influences step-wise attack performance, as well as its caveat. We also interpret why previous attempts of directly using raw gradients failed. Based on that, we further propose a new raw gradient descent (RGD) algorithm that eliminates the use of sign. Specifically, we convert the constrained optimization problem into an unconstrained one, by introducing a new hidden variable of non-clipped perturbation that can move beyond the constraint. The effectiveness of the proposed RGD algorithm has been demonstrated extensively in experiments, outperforming PGD and other competitors in various settings, without incurring any additional computational overhead. The codes is available in https://github.com/JunjieYang97/RGD.

For agents

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

get_harvested_code_for_paper("2312.01260")
get_code_for_paper("2312.01260")
have("2312.01260")

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

curl https://syntology.ai/api/ran/2312.01260.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.01260.svg)](https://syntology.ai/paper/2312.01260)

Connect an agent — have() is free.