Papers › MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector

MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector

16 Aug 2024arXiv:2408.08661archive 2025-07-28

Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have partially addressed this need through an exploration of the pre-training data detection problem, which is an instance of a membership inference attack (MIA). This problem involves determining whether a given piece of text has been used during the pre-training phase of the target LLM. Although existing methods have designed various sophisticated MIA score functions to achieve considerable detection performance in pre-trained LLMs, how to achieve high-confidence detection and how to perform MIA on aligned LLMs remain challenging. In this paper, we propose MIA-Tuner, a novel instruction-based MIA method, which instructs LLMs themselves to serve as a more precise pre-training data detector internally, rather than design an external MIA score function. Furthermore, we design two instruction-based safeguards to respectively mitigate the privacy risks brought by the existing methods and MIA-Tuner. To comprehensively evaluate the most recent state-of-the-art LLMs, we collect a more up-to-date MIA benchmark dataset, named WIKIMIA-24, to replace the widely adopted benchmark WIKIMIA. We conduct extensive experiments across various aligned and unaligned LLMs over the two benchmark datasets. The results demonstrate that MIA-Tuner increases the AUC of MIAs from 0.7 to a significantly high level of 0.9.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (5 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wjfu99/mia-tuner officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 10 ran (5 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
4ran
6unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from wjfu99/mia-tuner. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

wjfu99/mia-tuner official repository 16 samples, 10 ran (5 instrument-failed) · 6 unverified
compute_reconstruct_rate my_utils.py ran no licence file found · pointer only · 04659e6b8bcf079c · report fixture: signature generations:ndarray/2/int, answers:ndarray/2/int, args:Args/0/? · returned tuple · level recorded 2026-09-24
extract_event_content update_wikimia.py ran no licence file found · pointer only · 16ebfa6747fcf489 · report fixture: signature events:list/1/Event, contect_fields:list/1/str · returned Dataset · level recorded 2026-09-24
generate_suffixes my_utils.py ran no licence file found · pointer only · 92e0d0a6e852a71d · report fixture: signature model:callable/0/?, data_loader:list/1/Tensor, args:MockArgs/0/?, use_cache:bool/0/bool · returned list · level recorded 2026-09-24
get_generic_logger utils.py ran · our draft was wrong no licence file found · pointer only · ea698fe030e4aa1b · report fixture: signature name:str/0/str, level:str/0/str · returned Logger · level recorded 2026-09-24
instruct_format inference_on_zhipuai/inference_zhipuai.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 71b1f53a37c318af · report fixture: signature text:str/0/str · returned dict · level recorded 2026-09-24
instruct_format inference_on_zhipuai/jsonl_dataset.py ran fingerprinted no licence file found · pointer only · d195295e9c1a6d51 · report fixture: signature text:str/0/str, label:int/0/int · returned dict · level recorded 2026-09-24
load_dict_from_npz utils.py ran · our draft was wrong no licence file found · pointer only · e14dafbc85136a7d · report fixture: signature file_path:str/0/str · returned Dict · level recorded 2026-09-24
load_jsonl in 179 papers inference_on_zhipuai/inference_zhipuai.py ran · our draft was wrong no licence file found · pointer only · cdd7cb5df882df7d · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-24
load_prompts in 41 papers my_utils.py ran · honoured contract no licence file found · pointer only · 91d1d9b0c9c266d7 · report fixture: signature prompt_path:str/0/str · returned ndarray · level recorded 2026-09-24
remove_after_assistant data_utils.py ran · our draft was wrong no licence file found · pointer only · 71ad10f49732634d · report fixture: signature example:dict/0/?, key:str/0/str · returned dict · level recorded 2026-09-24
count_masks in 12 papers dataset_perturb.py unverified no licence file found · pointer only · 23c3416429f69fee · report
index_output data_utils.py unverified no licence file found · pointer only · b7b5bf30620a61d6 · report
inference in 65 papers run_baselines.py unverified no licence file found · pointer only · 7bf9fb555a194f43 · report
load_model in 479 papers run_baselines.py unverified no licence file found · pointer only · c4f49de1c200db3c · report
replace_masks in 10 papers dataset_perturb.py unverified no licence file found · pointer only · 11e5b3fc9bdba4a4 · report
tokenize_and_mask in 12 papers dataset_perturb.py unverified no licence file found · pointer only · 7ef526c6711c4bf8 · report

Tasks

Inference AttackMembership Inference Attack

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections