Papers › Mask Image Watermarking

Mask Image Watermarking

17 Apr 2025arXiv:2504.12739archive 2025-07-28

Runyi Hu, Jie Zhang, Shiqian Zhao, Nils Lukas, Jiwei Li, Qing Guo, Han Qiu, Tianwei Zhang

We present MaskMark, a simple, efficient, and flexible framework for image watermarking. MaskMark has two variants: (1) MaskMark-D, which supports global watermark embedding, watermark localization, and local watermark extraction for applications such as tamper detection; (2) MaskMark-ED, which focuses on local watermark embedding and extraction, offering enhanced robustness in small regions to support fine-grined image protection. MaskMark-D builds on the classical encoder-distortion layer-decoder training paradigm. In MaskMark-D, we introduce a simple masking mechanism during the decoding stage that enables both global and local watermark extraction. During training, the decoder is guided by various types of masks applied to watermarked images before extraction, helping it learn to localize watermarks and extract them from the corresponding local areas. MaskMark-ED extends this design by incorporating the mask into the encoding stage as well, guiding the encoder to embed the watermark in designated local regions, which improves robustness under regional attacks. Extensive experiments show that MaskMark achieves state-of-the-art performance in global and local watermark extraction, watermark localization, and multi-watermark embedding. It outperforms all existing baselines, including the recent leading model WAM for local watermarking, while preserving high visual quality of the watermarked images. In addition, MaskMark is highly efficient and adaptable. It requires only 20 hours of training on a single A6000 GPU, achieving 15x computational efficiency compared to WAM. By simply adjusting the distortion layer, MaskMark can be quickly fine-tuned to meet varying robustness requirements.

PaperPDFCodeCode Syntology ranMethod as code

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 23 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 11 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: 20 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); community: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 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 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. 3 of the 12 samples that ran have no recorded date.

hurunyi/maskmark officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 9 ran (2 instrument-failed) · 11 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

23 samples harvested: 12 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
7ran
11unverified

Licence: 0 of the 23 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 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. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

hurunyi/maskmark official repository 20 samples, 9 ran (2 instrument-failed) · 11 unverified
ConvNormRelu models/Network.py ran fingerprinted MIT (permissive) · 1f06faef62e6eba2 · report fixture: returned ConvNormRelu · level recorded 2026-09-22
DoubleConv in 23 papers
census: 8 implementations from 7 papers, 6 distinct outputs on one shared input
models/Network.py ran fingerprinted MIT (permissive) · e066873b6a3c1c9c · report fixture: returned DoubleConv · level recorded 2026-09-22
Down in 17 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models/Network.py ran fingerprinted MIT (permissive) · 29d6c8dc33aa60c4 · report fixture: returned Down · level recorded 2026-09-22
GroupNorm32 in 11 papers models/Network.py ran · our draft was wrong MIT (permissive) · 970af1a11b88823e · report fixture: signature channels:int/0/int · returned GroupNorm · level recorded 2026-09-22
REBNCONV models/Network.py ran fingerprinted MIT (permissive) · 12201d6ffa2f0b4d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RSU4 models/Network.py ran fingerprinted MIT (permissive) · 5f68a0c61f8c216a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
UNet in 40 papers models/Network.py ran MIT (permissive) · 0452d2e25645e27d · report fixture: returned UNet · level recorded 2026-09-22
Up in 24 papers models/Network.py ran MIT (permissive) · 65f0d74b6eff8968 · report fixture: returned Up · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 2 of 11, arg 1: rank 4, kind float, dtype float32
models/Network.py ran · our draft was wrong fingerprinted MIT (permissive) · 37f8b080682479a1 · report fixture: signature images:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Decoder in 210 papers models/Network.py unverified MIT (permissive) · 8d74faed004f7cc6 · report
Encoder in 278 papers models/Network.py unverified MIT (permissive) · 073c41c1803af624 · report
JND models/Network.py unverified MIT (permissive) · cda4a32b64c7392c · report
MaskWM models/Network.py unverified MIT (permissive) · b653f0e6310a39f5 · report
Noise in 9 papers models/Network.py unverified MIT (permissive) · 942910e44eb17b71 · report
RSU4F models/Network.py unverified MIT (permissive) · 7195700248a991a6 · report
RSU5 models/Network.py unverified MIT (permissive) · 50ca52394f8531f9 · report
RSU6 models/Network.py unverified MIT (permissive) · b0f104c5c1a11652 · report
RSU7 models/Network.py unverified MIT (permissive) · 7958e1bb9c073000 · report
U2NETP models/Network.py unverified MIT (permissive) · d4c76d061ef5a0e0 · report
WatermarkModel models/Network.py unverified MIT (permissive) · c7987731c99f5e9c · report
hurunyi/maskwm community 3 samples, 3 ran (3 instrument-failed) · 0 unverified
calculate_iou_score inference.py ran · our draft was wrong MIT (permissive) · a0b11efc95c79c73 · report fixture: signature preds:Tensor/2/float, targets:Tensor/2/float · returned tuple · level recorded, date not recorded
decoded_message_accuracy inference.py ran · our draft was wrong fingerprinted MIT (permissive) · 2978a72a8435838d · report fixture: signature message:Tensor/2/float, decoded_message:Tensor/2/float · returned float · level recorded, date not recorded
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 4, kind float, dtype float32
inference.py ran · our draft was wrong fingerprinted MIT (permissive) · 2d094cdb029a3669 · report fixture: signature images:Tensor/4/float · returned Tensor · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MaskWM (graph method: MaskWM). 23 bricks; individually on a fixture: 12 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. MaskWM entry · level 0 · unverified · b653f0e6310a39f5
  2. WatermarkModel model · level 0 · unverified · c7987731c99f5e9c
  3. denormalize helper · level 1 · ran · our draft was wrong · 2d094cdb029a3669
  4. Decoder model · level 0 · unverified · 8d74faed004f7cc6
  5. Encoder model · level 0 · unverified · 073c41c1803af624
  6. Noise helper · level 0 · unverified · 942910e44eb17b71
  7. ConvNormRelu helper · level 1 · ran · 1f06faef62e6eba2
  8. GroupNorm32 helper · level 1 · ran · our draft was wrong · 970af1a11b88823e
  9. U2NETP helper · level 0 · unverified · d4c76d061ef5a0e0
  10. UNet helper · level 1 · ran · 0452d2e25645e27d
  11. JND helper · level 0 · unverified · cda4a32b64c7392c
  12. normalize helper · level 1 · ran · our draft was wrong · 37f8b080682479a1
  13. RSU4 helper · level 1 · ran · 5f68a0c61f8c216a
  14. RSU4F helper · level 0 · unverified · 7195700248a991a6
  15. RSU5 helper · level 0 · unverified · 50ca52394f8531f9
  16. RSU6 helper · level 0 · unverified · b0f104c5c1a11652
  17. RSU7 helper · level 0 · unverified · 7958e1bb9c073000
  18. _upsample_like helper · level 1 · ran; the contract check could not run · bfdbf21066b9aaf1
  19. DoubleConv helper · level 1 · ran · e066873b6a3c1c9c
  20. Down helper · level 1 · ran · 29d6c8dc33aa60c4
  21. OutConv helper · level 1 · ran · 283a86aac0825bc9
  22. Up helper · level 1 · ran · 65f0d74b6eff8968
  23. REBNCONV helper · level 1 · ran · 12201d6ffa2f0b4d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2504.12739") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Computational EfficiencyDecoder

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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