SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.12865 · 2026

Proxy Robustness in Vision Language Models is Effortlessly Transferable

Lei Zhang, Fuxiang Huang, Xiaowei Fu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2601.12865.json · badge: /api/ran/2601.12865.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
fxw13/HPT-GPD community
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input
fxw13/HPT-GPD/models/prompters.py
pointer only (licence: NONE) · get_code("eafd21dd229fcdd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fxw13/HPT-GPD 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.

TokenPrompter_w_pos_TransformerGEN Ran
ran on a synthesized input · constructed an object; no result was computed
fxw13/HPT-GPD/models/prompters.py
pointer only (licence: NONE) · get_code("cc002684d48493c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fxw13/HPT-GPD 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.

Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
fxw13/HPT-GPD/models/prompters.py
pointer only (licence: NONE) · get_code("667c823b63da6145")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fxw13/HPT-GPD 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
Transformer
brick of this paper's assembly: model
11 other papers
11 dated earlier · 2 only as an assembly brick
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2101.11986 (2021-01)
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
2103.14899 (2021-03)
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
and 8 more not named here

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

As a pivotal technique for improving the defense of deep models, adversarial robustness transfer via distillation has demonstrated remarkable success in conventional image classification tasks. However, this paradigm encounters critical challenges when applied to vision-language models (VLM) (e.g., CLIP): constructing adversarially robust teacher for large-scale multi-modal models demands prohibitively high computational resources. We bridge this gap by revealing an interesting phenomenon: vanilla CLIP (without adversarial training) exhibits intrinsic defensive capabilities against adversarial examples generated by another CLIP with different architectures. We formally define this as proxy adversarial robustness, and naturally propose a Heterogeneous Proxy Transfer (HPT) framework that establishes cross-architectural robustness distillation channels between CLIP variants, effortlessly enabling the VLM robustness transfer from proxy to target models. Yet, such proxy transfer paradigm easily induces severe overfitting, leading to a sharp degradation in zero-shot natural generalization. To resolve that, we design Generalization-Pivot Decoupling (GPD) by leveraging the difference in learning rate scheduling. This decouples the proxy transfer process into a generalization-anchored warm-up that maintains generalization and a generalization-pulled HPT that promotes adversarial robustness, to achieve an equilibrium between natural generalization and adversarial robustness. Extensive experiments on 15 zero-shot datasets demonstrate the effectiveness of our HPT-GPD method. The code is available at the website of github.com/fxw13/HPT-GPD.

For agents

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

get_harvested_code_for_paper("2601.12865")
get_code_for_paper("2601.12865")
have("2601.12865")

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

curl https://syntology.ai/api/ran/2601.12865.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.12865.svg)](https://syntology.ai/paper/2601.12865)

Connect an agent — have() is free.