Papers › LLMmap: Fingerprinting For Large Language Models

LLMmap: Fingerprinting For Large Language Models

22 Jul 2024arXiv:2407.15847archive 2025-07-28

Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese

We introduce LLMmap, a first-generation fingerprinting technique targeted at LLM-integrated applications. LLMmap employs an active fingerprinting approach, sending carefully crafted queries to the application and analyzing the responses to identify the specific LLM version in use. Our query selection is informed by domain expertise on how LLMs generate uniquely identifiable responses to thematically varied prompts. With as few as 8 interactions, LLMmap can accurately identify 42 different LLM versions with over 95% accuracy. More importantly, LLMmap is designed to be robust across different application layers, allowing it to identify LLM versions--whether open-source or proprietary--from various vendors, operating under various unknown system prompts, stochastic sampling hyperparameters, and even complex generation frameworks such as RAG or Chain-of-Thought. We discuss potential mitigations and demonstrate that, against resourceful adversaries, effective countermeasures may be challenging or even unrealizable.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.15847")

Code

Syntology Ran 9 of 16 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 9 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pasquini-dario/LLMmap officialmentioned in papermentioned on GitHubtfMIT 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; 9 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9ran
7unverified

Licence: 0 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 pasquini-dario/LLMmap. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

build_templates pasquini-dario/LLMmap/LLMmap/templates.py official repository ran MIT (permissive) · 4d3e058045786b53 · report
euclidean_distance pasquini-dario/LLMmap/LLMmap/inference_model_archs.py official repository ran fingerprinted MIT (permissive) · 47203ac597d1cdaa · report
get_activation pasquini-dario/LLMmap/LLMmap/inference_model_archs.py official repository ran MIT (permissive) · 82f8654112f827f6 · report
predict_by_templates pasquini-dario/LLMmap/LLMmap/templates.py official repository ran MIT (permissive) · 63abcdbc162b0dc0 · report
read_conf_file pasquini-dario/LLMmap/LLMmap/utility.py official repository ran MIT (permissive) · 145223e448267f7f · report
read_dataset pasquini-dario/LLMmap/LLMmap/input_pipeline.py official repository ran MIT (permissive) · 6e7bb2069a548786 · report
read_pickle pasquini-dario/LLMmap/LLMmap/utility.py official repository ran MIT (permissive) · c7497cceeb28ffef · report
read_templates pasquini-dario/LLMmap/LLMmap/inference.py official repository ran MIT (permissive) · adc09759f8d65697 · report
sample_from_multi_universe pasquini-dario/LLMmap/LLMmap/prompt_configuration.py official repository ran MIT (permissive) · b448e7d58494a339 · report
infer_features pasquini-dario/LLMmap/LLMmap/templates.py official repository unverified MIT (permissive) · a5c7254402cb328d · report
load_LLMmap pasquini-dario/LLMmap/LLMmap/inference.py official repository unverified MIT (permissive) · a0c4036c783edf32 · report
load_datasets pasquini-dario/LLMmap/LLMmap/dataset.py official repository unverified MIT (permissive) · fe509b80ffd62e01 · report
load_model pasquini-dario/LLMmap/LLMmap/embedding_model.py official repository unverified MIT (permissive) · 9ee90e0c985481bb · report
make_norm pasquini-dario/LLMmap/LLMmap/inference_model_archs.py official repository unverified MIT (permissive) · 9cb6cf3f23bddfa5 · report
read_dataset pasquini-dario/LLMmap/LLMmap/dataset_maker.py official repository unverified MIT (permissive) · 5c38d3eecf731383 · report
train_model pasquini-dario/LLMmap/LLMmap/trainer.py official repository unverified MIT (permissive) · 3ce9e1b27efcd170 · report

Tasks

RAG

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBARTBERTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionRAGResidual ConnectionSoftmaxWeight DecayWordPiece

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