Papers › Evading Data Contamination Detection for Language Models is (too) Easy

Evading Data Contamination Detection for Language Models is (too) Easy

5 Feb 2024arXiv:2402.02823archive 2025-07-28

Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin Vechev

Large language models are widespread, with their performance on benchmarks frequently guiding user preferences for one model over another. However, the vast amount of data these models are trained on can inadvertently lead to contamination with public benchmarks, thus compromising performance measurements. While recently developed contamination detection methods try to address this issue, they overlook the possibility of deliberate contamination by malicious model providers aiming to evade detection. We argue that this setting is of crucial importance as it casts doubt on the reliability of public benchmarks. To more rigorously study this issue, we propose a categorization of both model providers and contamination detection methods. This reveals vulnerabilities in existing methods that we exploit with EAL, a simple yet effective contamination technique that significantly inflates benchmark performance while completely evading current detection methods.

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 12 code samples: 11 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 12: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 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: 7 samples from 1 repository, 4 ran (2 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

eth-sri/malicious-contamination officialmentioned in paperpytorchApache-2.0Syntology: 7 samples, 4 ran (2 instrument-failed) · 3 unverified report
thu-keg/dice mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 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

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 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
2ran
4unverified

Licence: 1 of the 12 samples is 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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.

eth-sri/malicious-contamination official repository 7 samples, 4 ran (2 instrument-failed) · 3 unverified
construct_prompt in 24 papers src/contamination/llm_decontaminator.py ran fingerprinted Apache-2.0 (permissive) · 255132d5b9dc4ec5 · report fixture: signature q1:str/0/str, q2:str/0/str, a1:str/0/str, a2:str/0/str · returned str · level recorded 2026-09-24
load_jsonl in 179 papers code-contamination-detection/src/analyze.py ran · our draft was wrong Apache-2.0 (permissive) · 4f7b998784e540eb · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-24
parse_question in 5 papers src/contamination/clean_eval.py ran · our draft was wrong Apache-2.0 (permissive) · 260501dfa9ae0d0f · report fixture: signature question:str/0/str, is_mc:bool/0/bool · returned tuple · level recorded 2026-09-24
process_raw src/contamination/clean_eval.py ran Apache-2.0 (permissive) · 6a30d1da83b8b62f · report fixture: signature json_content:list/1/dict, dataset:DataFrame/0/?, is_mc:bool/0/bool · returned DataFrame · level recorded 2026-09-24
evaluate_model in 54 papers code-contamination-detection/src/utils.py unverified Apache-2.0 (permissive) · 01d6eba772ddf7c2 · report
llm_decontaminator src/contamination/llm_decontaminator.py unverified Apache-2.0 (permissive) · 500c7cec099be76d · report
load_tokenizer in 66 papers src/contamination/basic_model_loader.py unverified Apache-2.0 (permissive) · c29c23246ee520ad · report
thu-keg/dice community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
generation_prompt_template OOD_test/scripts/contaminated_finetune.py ran · our draft was wrong fingerprinted MIT (permissive) · 925b9c7288304f71 · report fixture: signature instruction:str/0/str, input_:str/0/str · returned str · level recorded 2026-09-22
prompt_template OOD_test/scripts/contaminated_finetune.py ran · our draft was wrong fingerprinted MIT (permissive) · f94987f7381d494f · report fixture: signature instruction:str/0/str, input_:str/0/str · returned str · level recorded 2026-09-22
test_DINM Locate/DICE_locate.py ran · honoured contract MIT (permissive) · 47eafd807076448c · report fixture: signature edit_data_all:list/1/dict, editor:MinimalEditor/0/?, hparams:MinimalHParams/0/? · returned list · level recorded 2026-09-22
predict in 126 papers Locate/DICE_locate.py unverified MIT (permissive) · 8f12c20fe27a3248 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
read_json in 250 papers repository not located ran · our draft was wrong licence of this copy not recorded · f8c65c92ec213846 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-22

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