Papers › REEF: Representation Encoding Fingerprints for Large Language Models

REEF: Representation Encoding Fingerprints for Large Language Models

18 Oct 2024arXiv:2410.14273archive 2025-07-28

Jie Zhang, Dongrui Liu, Chen Qian, Linfeng Zhang, Yong liu, Yu Qiao, Jing Shao

Protecting the intellectual property of open-source Large Language Models (LLMs) is very important, because training LLMs costs extensive computational resources and data. Therefore, model owners and third parties need to identify whether a suspect model is a subsequent development of the victim model. To this end, we propose a training-free REEF to identify the relationship between the suspect and victim models from the perspective of LLMs' feature representations. Specifically, REEF computes and compares the centered kernel alignment similarity between the representations of a suspect model and a victim model on the same samples. This training-free REEF does not impair the model's general capabilities and is robust to sequential fine-tuning, pruning, model merging, and permutations. In this way, REEF provides a simple and effective way for third parties and models' owners to protect LLMs' intellectual property together. The code is available at https://github.com/tmylla/REEF.

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; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (3 with no instrument failure; 7 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. 1 of the 10 samples that ran has no recorded date.

tmylla/reef officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 10 ran (7 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; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 7 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
6ran · our draft was wrong
1ran; the contract check could not run
2ran
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 tmylla/reef. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

tmylla/reef official repository 16 samples, 10 ran (7 instrument-failed) · 6 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
src/utils.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 225e33b56e37c35d · report fixture: signature out:Tensor/2/float, y:Tensor/1/int · returned Tensor · level recorded 2026-09-24
attack in 16 papers src/ics.py ran no licence file found · pointer only · 2805e64d92a25d50 · report fixture: signature X_hat:Tensor/2/float, W_q:Tensor/2/float, W_k:Tensor/2/float, W_v:Tensor/2/float, W_o:Tensor/2/float, W_up:Tensor/2/float, W_down:Tensor/2/float, attack_type:str/0/str · returned tuple · level recorded 2026-09-24
compute_x src/logits.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a44746f0f405d665 · report fixture: signature W:Tensor/2/float, logit:Tensor/1/float · returned Tensor · level recorded 2026-09-24
cosine_similarity in 120 papers
census: 26 implementations from 30 papers, 11 distinct outputs across 5 buckets, one shared input per bucket
src/ics.py ran · our draft was wrong no licence file found · pointer only · c33e1a47ece4c17b · report fixture: signature tensor1:Tensor/1/float, tensor2:Tensor/1/float · returned float32 · level recorded 2026-09-24
create_adjacency_matrix src/train_cls_gcn.py ran · our draft was wrong no licence file found · pointer only · fe48eee1679ed89a · report fixture: signature features:Tensor/2/float, threshold:float/0/float · returned ndarray · level recorded 2026-09-24
get_acts in 7 papers src/generate_head_activations.py ran no licence file found · pointer only · a284aa5d43c3b70a · report fixture: signature statements:list/1/str, tokenizer:MinimalTokenizer/0/?, model:callable/0/?, device:str/0/str, token_pos:int/0/int · returned Tensor · level recorded 2026-09-24
get_model_save_path src/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7591741c636ad6ae · report fixture: signature model_tag:str/0/str · returned str · level recorded 2026-09-24
load_obj in 34 papers src/utils.py ran · our draft was wrong no licence file found · pointer only · 47f979c1e336d41b · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
load_statements in 5 papers src/generate_activations.py ran · our draft was wrong no licence file found · pointer only · f0cc63177ce8b7a1 · report fixture: signature dataset_name:str/0/str · returned list · level recorded, date not recorded
load_victim_logits src/logits.py ran · honoured contract no licence file found · pointer only · 73e7761c0aea5c73 · report fixture: signature smodel_tag:str/0/str · returned Tensor · level recorded 2026-09-24
create_adjacency_matrix src/transfer_cls.py unverified no licence file found · pointer only · 9b19f7a9671ea301 · report
get_acts in 7 papers src/generate_activations.py unverified no licence file found · pointer only · 9edbd42b20aaf225 · report
load_model in 479 papers src/generate_activations.py unverified no licence file found · pointer only · 9058a74d60bf8126 · report
load_suspect_logits src/logits.py unverified no licence file found · pointer only · 6488376eefc984d9 · report
train in 522 papers src/train_cls_gcn.py unverified no licence file found · pointer only · 66d2718c00dfd494 · report
validate in 313 papers src/train_cls_gcn.py unverified no licence file found · pointer only · 5b09c05b55d7fc25 · report

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