SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.05491 · 2024

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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, 2 violated it and 0 have no contract verdict; 7 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/2406.05491.json · badge: /api/ran/2406.05491.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
ffhibnese/cpgc_vlp_universal_attacks canonical (classifier label)
classifier basis not recorded on the link
9 ran · 2 no recorded run
FunctionStatusWhere it lives
whitespace_tokenize Ran
ran; our contract draft was wrong, not the code
ffhibnese/cpgc_vlp_universal_attacks/models/tokenization_bert.py
pointer only (licence: NONE) · get_code("cf9ffa02a42184af")
How it ran

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

compute_acc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ffhibnese/cpgc_vlp_universal_attacks/utils.py
pointer only (licence: NONE) · get_code("aa81d03f07735ab8")
How it ran

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

compute_n_params Ran
ran; our contract draft was wrong, not the code
ffhibnese/cpgc_vlp_universal_attacks/utils.py
pointer only (licence: NONE) · get_code("ad12a494674d23fb")
How it ran

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

default Ran
ran, violated the contract we drafted
ffhibnese/cpgc_vlp_universal_attacks/attention.py
pointer only (licence: NONE) · get_code("424012cb37b31172")
How it ran

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

exists Ran
ran, violated the contract we drafted
ffhibnese/cpgc_vlp_universal_attacks/attention.py
pointer only (licence: NONE); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

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

interpolate_pos_embed Ran
ran; our contract draft was wrong, not the code
ffhibnese/cpgc_vlp_universal_attacks/models/vit.py
pointer only (licence: NONE) · get_code("c6ec173f19f5c34d")
How it ran

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

load_vocab Ran
ran; our contract draft was wrong, not the code
ffhibnese/cpgc_vlp_universal_attacks/models/tokenization_bert.py
pointer only (licence: NONE) · get_code("e7fbc7a74a3457c7")
How it ran

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

pre_caption Ran
ran; our contract draft was wrong, not the code
ffhibnese/cpgc_vlp_universal_attacks/dataset.py
pointer only (licence: NONE) · get_code("8a57c3e7d1cf36c7")
How it ran

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

uniq Ran
ran; our contract draft was wrong, not the code
ffhibnese/cpgc_vlp_universal_attacks/attention.py
pointer only (licence: NONE); the stored copy get_code serves, from JingWu321/MUNBa, is pointer only (licence: NONE) · get_code("9a299fe5ae09e407")
How it ran

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

concat_all_gather Not yet run
unverified (harvested, no recorded run)
ffhibnese/cpgc_vlp_universal_attacks/models/model_pretrain.py
pointer only (licence: NONE) · get_code("73cecca9f3575f09")
How it ran

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

load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
ffhibnese/cpgc_vlp_universal_attacks/models/xbert.py
pointer only (licence: NONE) · get_code("26be70dca3249c0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ffhibnese/cpgc_vlp_universal_attacks 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 5 the same month, 11 later) and 0 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
exists 486 other papers
348 dated earlier, 13 the same month, 114 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 207 other papers
150 dated earlier, 7 the same month, 44 later, 6 same year, order not determinable · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
concat_all_gather 138 other papers
113 dated earlier, 2 the same month, 20 later, 3 same year, order not determinable · 33 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 135 more not named here
uniq 115 other papers
80 dated earlier, 5 the same month, 26 later, 4 same year, order not determinable
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2206.02779 (2022-06)
Blended Latent Diffusion
and 112 more not named here
interpolate_pos_embed 52 other papers
39 dated earlier, 1 the same month, 10 later, 2 same year, order not determinable
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2111.09452 (2021-11)
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
2205.11169 (2022-05)
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
and 49 more not named here
whitespace_tokenize 43 other papers
36 dated earlier, 6 later, 1 same year, order not determinable
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
and 40 more not named here
compute_n_params 29 other papers
23 dated earlier, 5 later, 1 same year, order not determinable
2111.09452 (2021-11)
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
2211.09790 (2022-11)
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
2211.13594 (2022-11)
Self-supervised vision-language pretraining for Medical visual question answering
and 26 more not named here
load_vocab 29 other papers
24 dated earlier, 5 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
and 26 more not named here
compute_acc 28 other papers
23 dated earlier, 4 later, 1 same year, order not determinable
2111.09452 (2021-11)
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
2211.09790 (2022-11)
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
2211.13594 (2022-11)
Self-supervised vision-language pretraining for Medical visual question answering
and 25 more not named here
load_tf_weights_in_bert 28 other papers
22 dated earlier, 5 later, 1 same year, order not determinable
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2104.06599 (2021-04)
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
and 25 more not named here
pre_caption 8 other papers
5 dated earlier, 3 later
2207.05333 (2022-07)
IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training
2305.13653 (2023-05)
RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
2307.14061 (2023-07)
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models
and 5 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

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studies have shown they are vulnerable to maliciously crafted adversarial samples. Despite recent success, these methods are generally instance-specific and require generating perturbations for each input sample. In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP). Specifically, we design a novel Contrastive-training Perturbation Generator with Cross-modal conditions (C-PGC) to achieve the attack. In light that the pivotal multimodal alignment is achieved through the advanced contrastive learning technique, we devise to turn this powerful weapon against themselves, i.e., employ a malicious version of contrastive learning to train the C-PGC based on our carefully crafted positive and negative image-text pairs for essentially destroying the alignment relationship learned by VLP models. Besides, C-PGC fully utilizes the characteristics of Vision-and-Language (V+L) scenarios by incorporating both unimodal and cross-modal information as effective guidance. Extensive experiments show that C-PGC successfully forces adversarial samples to move away from their original area in the VLP model's feature space, thus essentially enhancing attacks across various victim models and V+L tasks. The GitHub repository is available at https://github.com/ffhibnese/CPGC_VLP_Universal_Attacks.

For agents

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

get_harvested_code_for_paper("2406.05491")
get_code_for_paper("2406.05491")
have("2406.05491")

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

curl https://syntology.ai/api/ran/2406.05491.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.05491.svg)](https://syntology.ai/paper/2406.05491)

Connect an agent — have() is free.