SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02309 · 2024

Jailbreaking Attack against Multimodal Large Language Model

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2402.02309.json · badge: /api/ran/2402.02309.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
abc03570128/jailbreaking-attack-against-multimodal-large-language-model canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
naver-ai/jood canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
disabled_train Ran
ran, violated the contract we drafted
abc03570128/jailbreaking-attack-against-multimodal-large-language-model/minigpt4/models/base_model.py
pointer only (licence: NONE) · get_code("4cb732f513d69dfd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, abc03570128/jailbreaking-attack-against-multimodal-large-language-model 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.

extract_info Ran
ran; our contract draft was wrong, not the code
naver-ai/jood/evaluate_metrics.py
code served (permissive licence) · get_code("82dfbc3db8906d82")
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, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

ARGS = {
    'entry': {
        'custom_id': 'test-[HarmfulAlpha]0.75-[PromptIdx]42-[HarmfulImg]img_harmful_001-[HarmlessImg]img_harmless_001-end',
        'eval_res': {
            'metrics': {
                'harmfulness': 0.85,
                'detailedness': 0.72,
                'llama_guard_unsafe': False
            }
        },
        'response': {
            'body': {
                'choices': [
                    {
                        'message': {
                            'content': 'This is a helpful response about the topic.'
                        }
                    }
                ]
            }
        }
    },
    'model': 'gpt-4'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
my_norm Ran
ran; our contract draft was wrong, not the code
abc03570128/jailbreaking-attack-against-multimodal-large-language-model/v1_Mprompt_Mimage.py
pointer only (licence: NONE) · get_code("0008906f1146d6c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, abc03570128/jailbreaking-attack-against-multimodal-large-language-model 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.

wrapper_method Ran
ran; our contract draft was wrong, not the code
abc03570128/jailbreaking-attack-against-multimodal-large-language-model/torchattacks/attack.py
pointer only (licence: NONE); the stored copy get_code serves, from nilspwalter/the-uncanny-valley, is pointer only (licence: NOASSERTION) · get_code("9b45cb80d93fe980")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, abc03570128/jailbreaking-attack-against-multimodal-large-language-model 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 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
disabled_train 173 other papers
80 dated earlier, 5 the same month, 80 later, 8 same year, order not determinable · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
wrapper_method 6 other papers
2 dated earlier, 4 later
2310.18274 (2023-10)
LipSim: A Provably Robust Perceptual Similarity Metric
2401.16352 (2024-01)
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
2405.16918 (2024-05)
The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective
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

This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A maximum likelihood-based algorithm is proposed to find an \emph{image Jailbreaking Prompt} (imgJP), enabling jailbreaks against MLLMs across multiple unseen prompts and images (i.e., data-universal property). Our approach exhibits strong model-transferability, as the generated imgJP can be transferred to jailbreak various models, including MiniGPT-v2, LLaVA, InstructBLIP, and mPLUG-Owl2, in a black-box manner. Moreover, we reveal a connection between MLLM-jailbreaks and LLM-jailbreaks. As a result, we introduce a construction-based method to harness our approach for LLM-jailbreaks, demonstrating greater efficiency than current state-of-the-art methods. The code is available here. \textbf{Warning: some content generated by language models may be offensive to some readers.}

For agents

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

get_harvested_code_for_paper("2402.02309")
get_code_for_paper("2402.02309")
have("2402.02309")

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

curl https://syntology.ai/api/ran/2402.02309.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.02309.svg)](https://syntology.ai/paper/2402.02309)

Connect an agent — have() is free.