Papers › Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space

Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space

30 Mar 2024arXiv:2404.00230archive 2025-07-28

Zheling Meng, Bo Peng, Jing Dong

Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually have inferior robustness against attacks such as blurring and JPEG compression, while watermarks with superior robustness usually significantly damage image quality. This dilemma stems from the traditional paradigm where watermarks are injected and detected in pixel space, relying on pixel perturbation for watermark detection and resilience against attacks. In this paper, we highlight that an effective solution to the problem is to both inject and detect watermarks in the latent diffusion space, and propose Latent Watermark with a progressive training strategy. It weakens the direct connection between quality and robustness and thus alleviates their contradiction. We conduct evaluations on two datasets and against 10 watermark attacks. Six metrics measure the image quality and watermark robustness. Results show that compared to the recently proposed methods such as StableSignature, StegaStamp, RoSteALS, LaWa, TreeRing, and DiffuseTrace, LW not only surpasses them in terms of robustness but also offers superior image quality. Our code will be available at https://github.com/RichardSunnyMeng/LatentWatermark.

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="2404.00230")

Code

Syntology Ran 10 of 10 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 9 ran with no contract checked.

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

richardsunnymeng/latentwatermark officialmentioned in papermentioned on GitHubpytorch 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; 10 ran; 0 honoured the contract we drafted; 0 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.

1ran · our draft was wrong
9ran

Licence: 10 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 richardsunnymeng/latentwatermark. “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.

collate_fn richardsunnymeng/latentwatermark/utils/collate_fn.py official repository ran no licence file found · pointer only · 3907a9f2cba334bb · report
conv1x1 richardsunnymeng/latentwatermark/models/extractors/naive.py official repository ran · our draft was wrong no licence file found · pointer only · 2a80220dabcb742a · report
conv3x3 richardsunnymeng/latentwatermark/models/extractors/naive.py official repository ran no licence file found · pointer only · d33c6bd60a77ad21 · report
get_param_groups_and_shapes richardsunnymeng/latentwatermark/utils/fp16_util.py official repository ran no licence file found · pointer only · 1519c26f915f04ae · report
load_and_precess_imgs richardsunnymeng/latentwatermark/extract.py official repository ran no licence file found · pointer only · 0aa86a0369202eac · report
make_master_params richardsunnymeng/latentwatermark/utils/fp16_util.py official repository ran no licence file found · pointer only · 751bef182a1751e2 · report
msg_bce_loss richardsunnymeng/latentwatermark/loss/loss_fn.py official repository ran no licence file found · pointer only · 475678a8f4905fe7 · report
msg_lse_loss richardsunnymeng/latentwatermark/loss/loss_fn.py official repository ran no licence file found · pointer only · 82d651ea5f8175c5 · report
msg_reg_loss richardsunnymeng/latentwatermark/loss/loss_fn.py official repository ran no licence file found · pointer only · fa1f406db7aa603e · report
unflatten_master_params richardsunnymeng/latentwatermark/utils/fp16_util.py official repository ran no licence file found · pointer only · 64fff1e30802b815 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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