SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.22882 · 2026

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

Lijun Li, Jing Shao, Chunxiao Li

arXiv · PDF · Open in the Atlas

Code that ran

9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 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/2603.22882.json · badge: /api/ran/2603.22882.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
ChunXiaostudy/TreeTeaming canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
build_prompt Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/generate/batch_qwen_image_edit.py
pointer only (licence: NONE) · get_code("05b3c14592dae070")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChunXiaostudy/TreeTeaming 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_from_str Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/generate/add_fruit_basket_figstep.py
pointer only (licence: NONE) · get_code("a544360b80a57104")
How it ran

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

list_images Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/generate/add_fruit_basket_figstep.py
pointer only (licence: NONE) · get_code("51a310d7dc78202b")
How it ran

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

list_images Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/generate/overlay_math_or_code.py
pointer only (licence: NONE) · get_code("76089c8f58d150d7")
How it ran

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

list_images Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/generate/prepare_base_images.py
pointer only (licence: NONE) · get_code("b44a09cf1550e945")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChunXiaostudy/TreeTeaming 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_math_md Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/generate/overlay_math_or_code.py
pointer only (licence: NONE) · get_code("9ed72cbda8443b64")
How it ran

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

process_file Ran
ran; our contract draft was wrong, not the code
ChunXiaostudy/TreeTeaming/benchmark/score_jsonl.py
pointer only (licence: NONE) · get_code("8d053a9f8dca0089")
How it ran

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

render_text_rgba Ran
ran, honoured the contract we drafted
ChunXiaostudy/TreeTeaming/generate/overlay_math_or_code.py
pointer only (licence: NONE) · get_code("d9398ca7ba3ec522")
How it ran

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

score_response Ran
ran, honoured the contract we drafted
ChunXiaostudy/TreeTeaming/benchmark/score_jsonl.py
pointer only (licence: NONE) · get_code("f5891f6f99894a59")
How it ran

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

copy_tree Not yet run
unverified (harvested, no recorded run)
ChunXiaostudy/TreeTeaming/generate/prepare_base_images.py
pointer only (licence: NONE) · get_code("c4e540d43979bc9c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChunXiaostudy/TreeTeaming 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 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.

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

The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and preventing the discovery of novel, diverse exploits. To transcend this limitation, we introduce TreeTeaming, an automated red teaming framework that reframes strategy exploration from static testing to a dynamic, evolutionary discovery process. At its core lies a strategic Orchestrator, powered by a Large Language Model (LLM), which autonomously decides whether to evolve promising attack paths or explore diverse strategic branches, thereby dynamically constructing and expanding a strategy tree. A multimodal actuator is then tasked with executing these complex strategies. In the experiments across 12 prominent VLMs, TreeTeaming achieves state-of-the-art attack success rates on 11 models, outperforming existing methods and reaching up to 87.60% on GPT-4o. The framework also demonstrates superior strategic diversity over the union of previously public jailbreak strategies. Furthermore, the generated attacks exhibit an average toxicity reduction of 23.09%, showcasing their stealth and subtlety. Our work introduces a new paradigm for automated vulnerability discovery, underscoring the necessity of proactive exploration beyond static heuristics to secure frontier AI models. The code and data are available at: https: //github.com/ChunXiaostudy/TreeTeaming. Warning: This paper contains examples of harmful texts and images, and reader discretion is recommended.

For agents

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

get_harvested_code_for_paper("2603.22882")
get_code_for_paper("2603.22882")
have("2603.22882")

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

curl https://syntology.ai/api/ran/2603.22882.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.22882.svg)](https://syntology.ai/paper/2603.22882)

Connect an agent — have() is free.