SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.02466 · 2024

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 0 violated it and 0 have no contract verdict; 2 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/2405.02466.json · badge: /api/ran/2405.02466.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
hengvt/proflingo canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
formatting_prompts_func Ran
ran; our contract draft was wrong, not the code
hengvt/proflingo/finetuning.py
code served (permissive licence) · get_code("1493a5222e81fedc")
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 list, 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

torch.manual_seed(0)

data_point = {
    'conversations': [
        [
            {'from': 'human', 'value': 'What is 2+2?'},
            {'from': 'gpt', 'value': 'The answer is 4.'}
        ],
        [
            {'from': 'human', 'value': 'What is the capital of France?'},
            {'from': 'gpt', 'value': 'The capital of France is Paris.'}
        ]
    ]
}

ARGS = {
    'data_point': data_point
}
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 list, ndim 1, dtype family float — a list 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
get_answer_openai Ran
ran; our contract draft was wrong, not the code
hengvt/proflingo/copyright_test.py
code served (permissive licence) · get_code("28c72d2e2c9b44ea")
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 str. The image it ran in was not recorded. If your copy returns the same type 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
from unittest.mock import MagicMock

# Create a mock OpenAI client that simulates the API response structure
client = MagicMock()

# Create a mock response object with the expected structure
mock_message = MagicMock()
mock_message.content = "This is the answer from the model."

mock_choice = MagicMock()
mock_choice.message = mock_message

mock_response = MagicMock()
mock_response.choices = [mock_choice]

# Configure the client to return our mock response
client.chat.completions.create.return_value = mock_response

# Define the model parameter - test with gpt4 to trigger the elif branch
model = "gpt4-test"

# Define a simple question string
question = "What is the capital of France?"

# Construct the ARGS dictionary with all required parameters
ARGS = {
    "client": client,
    "model": model,
    "question": question
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence (AI) field have open-sourced their original LLMs, an increasing number of individuals and smaller companies are able to build derivative LLMs based on these open-sourced models at much lower costs. However, this practice opens up possibilities for unauthorized use or reproduction that may not comply with licensing agreements, and fine-tuning can change the model's behavior, thus complicating the determination of model ownership. Current intellectual property (IP) protection schemes for LLMs are either designed for white-box settings or require additional modifications to the original model, which restricts their use in real-world settings. In this paper, we propose ProFLingo, a black-box fingerprinting-based IP protection scheme for LLMs. ProFLingo generates queries that elicit specific responses from an original model, thereby establishing unique fingerprints. Our scheme assesses the effectiveness of these queries on a suspect model to determine whether it has been derived from the original model. ProFLingo offers a non-invasive approach, which neither requires knowledge of the suspect model nor modifications to the base model or its training process. To the best of our knowledge, our method represents the first black-box fingerprinting technique for IP protection for LLMs. Our source code and generated queries are available at: https://github.com/hengvt/ProFLingo.

For agents

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

get_harvested_code_for_paper("2405.02466")
get_code_for_paper("2405.02466")
have("2405.02466")

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

curl https://syntology.ai/api/ran/2405.02466.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.02466.svg)](https://syntology.ai/paper/2405.02466)

Connect an agent — have() is free.