SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09766 · ICLR · 2024

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

Philip Torr, Jindong Gu, Haochen Luo, Fengyuan Liu

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 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/2403.09766.json · badge: /api/ran/2403.09766.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
Haochen-Luo/CroPA canonical (classifier label)
classifier basis not recorded on the link
7 ran · 3 no recorded run
FunctionStatusWhere it lives
get_imports Ran
ran; our contract draft was wrong, not the code
Haochen-Luo/CroPA/transformers/dynamic_module_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from JD-GenX/Uni-AdGen, is pointer only (licence: NONE) · get_code("1adcf2d05b2faed1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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_relative_import_files Ran
ran; our contract draft was wrong, not the code
Haochen-Luo/CroPA/transformers/dynamic_module_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from JD-GenX/Uni-AdGen, is pointer only (licence: NONE) · get_code("518f6a89865f25d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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_relative_imports Ran
ran; our contract draft was wrong, not the code
Haochen-Luo/CroPA/transformers/dynamic_module_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from JD-GenX/Uni-AdGen, is pointer only (licence: NONE) · get_code("4af5faa701d0f2c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

infer_metric_tags_from_eval_results Ran
ran; our contract draft was wrong, not the code
Haochen-Luo/CroPA/transformers/modelcard.py
pointer only (licence: NONE); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("dd8f7751ef859581")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

parse_keras_history Ran
ran; our contract draft was wrong, not the code
Haochen-Luo/CroPA/transformers/modelcard.py
pointer only (licence: NONE) · get_code("a4491b45d19b7a39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

quick_gelu Ran
ran, honoured the contract we drafted
Haochen-Luo/CroPA/transformers/modeling_flax_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("a66d2b78670c85e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

rename_key_and_reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Haochen-Luo/CroPA/transformers/modeling_flax_pytorch_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("30d50ff2ced6b7a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

dtype_byte_size Not yet run
unverified (harvested, no recorded run)
Haochen-Luo/CroPA/transformers/modeling_flax_utils.py
pointer only (licence: NONE) · get_code("9d98806acb3144b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

flax_shard_checkpoint Not yet run
unverified (harvested, no recorded run)
Haochen-Luo/CroPA/transformers/modeling_flax_utils.py
pointer only (licence: NONE) · get_code("e3ce70ca9258800e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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.

is_hf_dataset Not yet run
unverified (harvested, no recorded run)
Haochen-Luo/CroPA/transformers/modelcard.py
pointer only (licence: NONE); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("ec7b1528a936234d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Haochen-Luo/CroPA 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 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, 10 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 10 the same month, 10 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
infer_metric_tags_from_eval_results 19 other papers
8 dated earlier, 1 the same month, 10 later
2022.findings-emnlp.427 (2022 (year only))
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
and 16 more not named here
quick_gelu 17 other papers
9 dated earlier, 1 the same month, 7 later
2022.findings-emnlp.427 (2022 (year only))
2303.14582 (2023-03)
Identification of Negative Transfers in Multitask Learning Using Surrogate Models
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 14 more not named here
is_hf_dataset 16 other papers
5 dated earlier, 1 the same month, 10 later
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 13 more not named here
parse_keras_history 16 other papers
5 dated earlier, 1 the same month, 10 later
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 13 more not named here
flax_shard_checkpoint 14 other papers
7 dated earlier, 1 the same month, 6 later
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
and 11 more not named here
dtype_byte_size 12 other papers
7 dated earlier, 1 the same month, 4 later
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
and 9 more not named here
get_relative_import_files 7 other papers
1 the same month, 6 later
2403.13263 (2024-03)
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
2406.02395 (2024-06)
GrootVL: Tree Topology is All You Need in State Space Model
2502.13963 (2025-02)
MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads
and 4 more not named here
get_relative_imports 7 other papers
1 the same month, 6 later
2403.13263 (2024-03)
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
2406.02395 (2024-06)
GrootVL: Tree Topology is All You Need in State Space Model
2502.13963 (2025-02)
MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads
and 4 more not named here
rename_key_and_reshape_tensor 7 other papers
1 the same month, 6 later
2403.13263 (2024-03)
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
2406.02395 (2024-06)
GrootVL: Tree Topology is All You Need in State Space Model
2502.13963 (2025-02)
MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads
and 4 more not named here
get_imports 6 other papers
1 the same month, 5 later
2403.13263 (2024-03)
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
2406.02395 (2024-06)
GrootVL: Tree Topology is All You Need in State Space Model
2505.19235 (2025-05)
CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
and 3 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

Different from traditional task-specific vision models, recent large VLMs can readily adapt to different vision tasks by simply using different textual instructions, i.e., prompts. However, a well-known concern about traditional task-specific vision models is that they can be misled by imperceptible adversarial perturbations. Furthermore, the concern is exacerbated by the phenomenon that the same adversarial perturbations can fool different task-specific models. Given that VLMs rely on prompts to adapt to different tasks, an intriguing question emerges: Can a single adversarial image mislead all predictions of VLMs when a thousand different prompts are given? This question essentially introduces a novel perspective on adversarial transferability: cross-prompt adversarial transferability. In this work, we propose the Cross-Prompt Attack (CroPA). This proposed method updates the visual adversarial perturbation with learnable prompts, which are designed to counteract the misleading effects of the adversarial image. By doing this, CroPA significantly improves the transferability of adversarial examples across prompts. Extensive experiments are conducted to verify the strong cross-prompt adversarial transferability of CroPA with prevalent VLMs including Flamingo, BLIP-2, and InstructBLIP in various different tasks. Our source code is available at https://github.com/Haochen-Luo/CroPA.

For agents

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

get_harvested_code_for_paper("2403.09766")
get_code_for_paper("2403.09766")
have("2403.09766")

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

curl https://syntology.ai/api/ran/2403.09766.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.09766.svg)](https://syntology.ai/paper/2403.09766)

Connect an agent — have() is free.