SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.17645 · ICLR · 2024

PUBDEF: DEFENDING AGAINST TRANSFER ATTACKS FROM PUBLIC MODELS

U Berkeley, Chawin Sitawarin, David Wagner, Jaewon Chang, David Huang, Wesson Altoyan

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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, 1 violated it and 0 have no contract verdict; 8 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/2310.17645.json · badge: /api/ran/2310.17645.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
ZhengyuZhao/TransferAttackEval canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
TI_multi Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZhengyuZhao/TransferAttackEval/attacks/input_augmentation_attacks.py
pointer only (licence: NONE) · get_code("54085cfa802ab165")
How it ran

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

accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZhengyuZhao/TransferAttackEval/attacks/utils_data.py
pointer only (licence: NONE) · get_code("713cbb90b09f2f2d")
How it ran

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

avg Ran
ran, violated the contract we drafted
ZhengyuZhao/TransferAttackEval/attacks/feature_disruption_attacks.py
pointer only (licence: NONE) · get_code("7a1a277b5455acbd")
How it ran

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

backward_hook Ran
ran; our contract draft was wrong, not the code
ZhengyuZhao/TransferAttackEval/attacks/surrogate_refinement_attacks.py
pointer only (licence: NONE) · get_code("c753988805f48831")
How it ran

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

backward_hook_norm Ran
ran; our contract draft was wrong, not the code
ZhengyuZhao/TransferAttackEval/attacks/surrogate_refinement_attacks.py
pointer only (licence: NONE) · get_code("411972c3dc337b0d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhengyuZhao/TransferAttackEval 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
ZhengyuZhao/TransferAttackEval/attacks/utils_iaa.py
pointer only (licence: NONE); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhengyuZhao/TransferAttackEval 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
ZhengyuZhao/TransferAttackEval/attacks/utils_iaa.py
pointer only (licence: NONE); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
How it ran

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

gkern Ran
ran, honoured the contract we drafted
ZhengyuZhao/TransferAttackEval/attacks/input_augmentation_attacks.py
pointer only (licence: NONE) · get_code("c7faa7d1457e3557")
How it ran

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

linbp_forw_resnet50 Ran
ran; our contract draft was wrong, not the code
ZhengyuZhao/TransferAttackEval/attacks/surrogate_refinement_attacks.py
pointer only (licence: NONE) · get_code("20790bad3577ddcb")
How it ran

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

sow_images Ran
ran; our contract draft was wrong, not the code
ZhengyuZhao/TransferAttackEval/attacks/feature_disruption_attacks.py
pointer only (licence: NONE) · get_code("6dd3f399496d6497")
How it ran

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

TI Not yet run
unverified (harvested, no recorded run)
ZhengyuZhao/TransferAttackEval/attacks/input_augmentation_attacks.py
pointer only (licence: NONE) · get_code("7ce71b5da4faa32b")
How it ran

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

resnet50 Not yet run
unverified (harvested, no recorded run)
ZhengyuZhao/TransferAttackEval/attacks/utils_iaa.py
pointer only (licence: NONE) · get_code("bfc5e139026a885d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhengyuZhao/TransferAttackEval 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 2 later) and 6 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 112 other papers
51 dated earlier, 6 the same month, 53 later, 2 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
53 dated earlier, 6 the same month, 50 later, 2 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
avg 1 other paper
1 dated earlier
2104.08303 (2021-04)
Capturing Row and Column Semantics in Transformer Based Question Answering over Tables
backward_hook 1 other paper
1 dated earlier
2002.05990 (2020-02)
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
backward_hook_norm 1 other paper
1 dated earlier
2002.05990 (2020-02)
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
linbp_forw_resnet50 1 other paper
1 dated earlier
2012.03528 (2020-12)
Backpropagating Linearly Improves Transferability of Adversarial 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

Adversarial attacks have been a looming and unaddressed threat in the industry. However, through a decade-long history of the robustness evaluation literature, we have learned that mounting a strong or optimal attack is challenging. It requires both machine learning and domain expertise. In other words, the white-box threat model, religiously assumed by a large majority of the past literature, is unrealistic. In this paper, we propose a new practical threat model where the adversary relies on transfer attacks through publicly available surrogate models. We argue that this setting will become the most prevalent for security-sensitive applications in the future. We evaluate the transfer attacks in this setting and propose a specialized defense method based on a game-theoretic perspective. The defenses are evaluated under 24 public models and 11 attack algorithms across three datasets (CIFAR-10, CIFAR-100, and ImageNet). Under this threat model, our defense, PUBDEF, outperforms the state-of-the-art white-box adversarial training by a large margin with almost no loss in the normal accuracy. For instance, on ImageNet, our defense achieves 62% accuracy under the strongest transfer attack vs only 36% of the best adversarially trained model. Its accuracy when not under attack is only 2% lower than that of an undefended model (78% vs 80%). Code is available here.

For agents

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

get_harvested_code_for_paper("2310.17645")
get_code_for_paper("2310.17645")
have("2310.17645")

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

curl https://syntology.ai/api/ran/2310.17645.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.17645.svg)](https://syntology.ai/paper/2310.17645)

Connect an agent — have() is free.