Papers › Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS...

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark

17 May 2023arXiv:2305.10036archive 2025-07-28

Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun, Xing Xie

Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language processing (NLP) tasks for customers. However, previous studies have shown that EaaS is vulnerable to model extraction attacks, which can cause significant losses for the owners of LLMs, as training these models is extremely expensive. To protect the copyright of LLMs for EaaS, we propose an Embedding Watermark method called EmbMarker that implants backdoors on embeddings. Our method selects a group of moderate-frequency words from a general text corpus to form a trigger set, then selects a target embedding as the watermark, and inserts it into the embeddings of texts containing trigger words as the backdoor. The weight of insertion is proportional to the number of trigger words included in the text. This allows the watermark backdoor to be effectively transferred to EaaS-stealer's model for copyright verification while minimizing the adverse impact on the original embeddings' utility. Our extensive experiments on various datasets show that our method can effectively protect the copyright of EaaS models without compromising service quality.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2305.10036")

Code

Syntology Ran 2 of 10 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yjw1029/embmarker officialmentioned in paperpytorchMIT 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

10 samples harvested; 2 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran
8unverified

Licence: 0 of the 10 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 yjw1029/EmbMarker. “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.

BackDoorClassifyOutput yjw1029/EmbMarker/src/model/copier/bert.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 903f1433d8d2db1f · report
BertForClassifyWithBackDoor yjw1029/EmbMarker/src/model/copier/bert.py official repository ran MIT (permissive) · 86093b919ea4359f · report
convert_mind_tsv_dict yjw1029/embmarker/src/dataset/utils.py official repository unverified MIT (permissive) · 1c3e5679dd810aea · report
eval_copier yjw1029/embmarker/src/run_gpt_backdoor.py official repository unverified MIT (permissive) · b3400e6c8205d71d · report
flatten yjw1029/embmarker/src/utils.py official repository unverified MIT (permissive) · f77001035699a79b · report
get_label_dict yjw1029/embmarker/src/dataset/utils.py official repository unverified MIT (permissive) · 2d6b92ecffe170d3 · report
load_gpt_embeds yjw1029/embmarker/src/dataset/emb_cache.py official repository unverified MIT (permissive) · a56d8bae91268b94 · report
load_mind yjw1029/embmarker/src/dataset/utils.py official repository unverified MIT (permissive) · 77269134ce3b18bc · report
merge_flatten_metrics yjw1029/embmarker/src/utils.py official repository unverified MIT (permissive) · 37ec69a16ec99bbd · report
train_copier yjw1029/embmarker/src/run_gpt_backdoor.py official repository unverified MIT (permissive) · 5bbc5ec0e19a75ed · report

Tasks

Model extraction

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