Papers › Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership...

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution

8 May 2024arXiv:2405.04825archive 2025-07-28

Shuo Shao, Yiming Li, Hongwei Yao, Yiling He, Zhan Qin, Kui Ren

Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors (i.e., backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status (i.e., misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, i.e., Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks (e.g., image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.

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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 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: 11 samples from 1 repository, 9 ran (5 with no instrument failure; 4 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.

shaoshuo-ss/eaaw officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 9 ran (4 instrument-failed) · 2 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 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.

2ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
3ran
2unverified

Licence: 0 of the 11 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 shaoshuo-ss/eaaw. “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.

shaoshuo-ss/eaaw official repository 11 samples, 9 ran (4 instrument-failed) · 2 unverified
bit_error_rate text-generation/watermark.py ran fingerprinted MIT (permissive) · 2d6eb3941ded6ba3 · report fixture: signature source:ndarray/1/int, target:ndarray/1/int · returned float64 · level recorded 2026-09-24
dec2bin in 5 papers image-classification/watermark/lime.py ran · honoured contract fingerprinted MIT (permissive) · 9e45f2f8ecb4d6ba · report fixture: signature num:int/0/int, length:int/0/int · returned list · level recorded 2026-09-24
evaluate_watermark text-generation/watermark.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 5a2d581963fed9bb · report fixture: signature weights:ndarray/1/int, target:ndarray/1/int · returned tuple · level recorded 2026-09-24
get_resnet18 in 9 papers image-classification/utils/models.py ran · our draft was wrong MIT (permissive) · f8a98d97abed03ba · report fixture: signature args:Args/0/? · returned ResNet · level recorded 2026-09-24
get_resnet34 in 7 papers image-classification/utils/models.py ran · our draft was wrong MIT (permissive) · 3b3524a6b7e9fdb1 · report fixture: signature args:Args/0/? · returned ResNet · level recorded 2026-09-24
get_resnet50 in 5 papers image-classification/utils/models.py ran · our draft was wrong MIT (permissive) · ef3f911aaa6673a2 · report fixture: signature args:Args/0/? · returned ResNet · level recorded 2026-09-24
init_watermark text-generation/watermark.py ran · honoured contract fingerprinted MIT (permissive) · e608aee2acfd059c · report fixture: signature wm_length:int/0/int · returned ndarray · level recorded 2026-09-24
select_random_noise_data image-classification/watermark/watermark.py ran MIT (permissive) · 56f802ee07886304 · report fixture: signature trigger_size:int/0/int, image_size:int/0/int, num_channels:int/0/int, num_classes:int/0/int · returned tuple · level recorded 2026-09-24
select_triggered_data image-classification/watermark/watermark.py ran MIT (permissive) · 0477bd7d1f9b2e33 · report fixture: signature train_dataset:SimpleDataset/0/?, trigger_size:int/0/int, wrong_label:bool/0/bool · returned tuple · level recorded 2026-09-24
get_fixed_trigger image-classification/watermark/watermark.py unverified MIT (permissive) · 4a67b032f6b32ae9 · report
get_full_dataset image-classification/utils/datasets.py unverified MIT (permissive) · 49e9a8310a77bfdf · report

Tasks

Explainable artificial intelligenceImage ClassificationText Generationimage-classification

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