SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00671 · NeurIPS · 2021

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

Zhuolin Yang, Linyi Li, Ce Zhang, Bo Li, Pan Zhou, Shiliang Zuo, Xiaojun Xu, Qian Chen, Benjamin Rubinstein

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2104.00671.json · badge: /api/ran/2104.00671.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
AI-secure/Transferability-Reduced-Smooth-Ensemble marked official in Papers with Code
Papers with Code archive
4 ran · 2 no recorded run
yuxiaochen1103/Hi-TRS extension (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_acc Ran
ran; our contract draft was wrong, not the code
yuxiaochen1103/Hi-TRS/train_on_NTU_AR.py
code served (permissive licence) · get_code("5f27b8e9e500314b")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float64, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:02:52Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create score tensor: batch_size=2, num_classes=4
# The function calls np.argmax(score, axis=1), so we need shape (batch_size, num_classes)
score = torch.randn(2, 4)

# Create labels tensor: batch_size=2
# The function compares outputs (from argmax) with labels
labels = torch.tensor([0, 2])

ARGS = {
    "score": score,
    "labels": labels,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Cosine Ran
ran, honoured the contract we drafted
AI-secure/Transferability-Reduced-Smooth-Ensemble/train/Empirical/trainer.py
pointer only (licence: NONE) · get_code("c5b926bdf355c69d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/Transferability-Reduced-Smooth-Ensemble 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.

Ensemble Ran
ran on a synthesized input · constructed an object; no result was computed
AI-secure/Transferability-Reduced-Smooth-Ensemble/train/Empirical/trainer.py
pointer only (licence: NONE) · get_code("26fd974a366fee7c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/Transferability-Reduced-Smooth-Ensemble 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.

Magnitude Ran
ran, honoured the contract we drafted
AI-secure/Transferability-Reduced-Smooth-Ensemble/train/Empirical/trainer.py
pointer only (licence: NONE) · get_code("d7d02143411ad4d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/Transferability-Reduced-Smooth-Ensemble 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.

PGD Ran
ran; our contract draft was wrong, not the code
AI-secure/Transferability-Reduced-Smooth-Ensemble/train/Empirical/trainer.py
pointer only (licence: NONE) · get_code("55b27593beb14f70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/Transferability-Reduced-Smooth-Ensemble 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_acc Ran
ran; our contract draft was wrong, not the code
yuxiaochen1103/Hi-TRS/pretrain_on_NTU.py
code served (permissive licence) · get_code("a1d3eaa48d595276")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float64, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create score tensor: shape (2, 4) - batch size 2, 4 classes
score = torch.randn(2, 4)

# Create labels tensor: shape (2,) - batch size 2, with class indices
labels = torch.tensor([0, 2], dtype=torch.long)

# Create mask tensor: shape (2,) - all ones to include all samples
mask = torch.tensor([1, 1], dtype=torch.long)

ARGS = {
    "score": score,
    "labels": labels,
    "mask": mask,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
TRS_Trainer Not yet run
unverified (harvested, no recorded run)
AI-secure/Transferability-Reduced-Smooth-Ensemble/train/Empirical/trainer.py
pointer only (licence: NONE) · get_code("fcc8bbcd4177bb70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/Transferability-Reduced-Smooth-Ensemble 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.

requires_grad_ Not yet run
unverified (harvested, no recorded run)
AI-secure/Transferability-Reduced-Smooth-Ensemble/train/Empirical/trainer.py
pointer only (licence: NONE) · get_code("0122889949b64757")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/Transferability-Reduced-Smooth-Ensemble 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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, 0 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
requires_grad_
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2009.14720 (2020-09)
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
2102.05096 (2021-02)
Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples
Ensemble
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2009.14720 (2020-09)
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

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 Transferability is an intriguing property -adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better protect ML systems against adversarial attacks, several questions are raised: what are the sufficient conditions for adversarial transferability and how to bound it? Is there a way to reduce the adversarial transferability in order to improve the robustness of an ensemble ML model? To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness. Our theoretical analysis shows that only promoting the orthogonality between gradients of base models is not enough to ensure low transferability; in the meantime, the model smoothness is an important factor to control the transferability. We also provide the lower and upper bounds of adversarial transferability under certain conditions. Inspired by our theoretical analysis, we propose an effective Transferability Reduced Smooth (TRS) ensemble training strategy to train a robust ensemble with low transferability by enforcing both gradient orthogonality and model smoothness between base models. We conduct extensive experiments on TRS and compare with 6 state-of-the-art ensemble baselines against 8 whitebox attacks on different datasets, demonstrating that the proposed TRS outperforms all baselines significantly.

For agents

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

get_harvested_code_for_paper("2104.00671")
get_code_for_paper("2104.00671")
have("2104.00671")

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

curl https://syntology.ai/api/ran/2104.00671.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.00671.svg)](https://syntology.ai/paper/2104.00671)

Connect an agent — have() is free.