Papers › UnMarker: A Universal Attack on Defensive Image Watermarking

UnMarker: A Universal Attack on Defensive Image Watermarking

14 May 2024arXiv:2405.08363archive 2025-07-28

Andre Kassis, Urs Hengartner

Reports regarding the misuse of Generative AI (GenAI) to create deepfakes are frequent. Defensive watermarking enables GenAI providers to hide fingerprints in their images and use them later for deepfake detection. Yet, its potential has not been fully explored. We present UnMarker -- the first practical universal attack on defensive watermarking. Unlike existing attacks, UnMarker requires no detector feedback, no unrealistic knowledge of the watermarking scheme or similar models, and no advanced denoising pipelines that may not be available. Instead, being the product of an in-depth analysis of the watermarking paradigm revealing that robust schemes must construct their watermarks in the spectral amplitudes, UnMarker employs two novel adversarial optimizations to disrupt the spectra of watermarked images, erasing the watermarks. Evaluations against SOTA schemes prove UnMarker's effectiveness. It not only defeats traditional schemes while retaining superior quality compared to existing attacks but also breaks semantic watermarks that alter an image's structure, reducing the best detection rate to 43% and rendering them useless. To our knowledge, UnMarker is the first practical attack on semantic watermarks, which have been deemed the future of defensive watermarking. Our findings show that defensive watermarking is not a viable defense against deepfakes, and we urge the community to explore alternatives.

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="2405.08363")

Code

Syntology Ran 14 of 19 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

andrekassis/ai-watermark officialmentioned on GitHubpytorchNOASSERTION 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

19 samples harvested; 14 ran; 2 honoured the contract we drafted; 5 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.

2ran · honoured contract
3ran · our draft was wrong
2ran · fixture could not drive it
7ran
5unverified

Licence: 19 of the 19 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 andrekassis/ai-watermark. “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.

approx_standard_normal_cdf andrekassis/ai-watermark/modules/attack/diffusion/gaussian_diffusion.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · cfd76fd0d89574a4 · report
compute_det_curve andrekassis/ai-watermark/modules/metrics.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 3a889d3debbcead8 · report
compute_eer andrekassis/ai-watermark/modules/metrics.py official repository ran fingerprinted licence not identified · pointer only · 7a62f8b12ad13309 · report
dict_to_str andrekassis/ai-watermark/attack.py official repository ran licence not identified · pointer only · 310ee02a872957c1 · report
discretized_gaussian_log_likelihood andrekassis/ai-watermark/modules/attack/diffusion/gaussian_diffusion.py official repository ran · our draft was wrong no licence file found · pointer only · cd33283d615fb3d7 · report
fix_state_dict andrekassis/ai-watermark/modules/training.py official repository ran licence not identified · pointer only · 1b729f41e358fb79 · report
get_param_groups_and_shapes andrekassis/ai-watermark/modules/attack/diffusion/fp16_util.py official repository ran no licence file found · pointer only · e41367ad14ff58fd · report
get_probs andrekassis/ai-watermark/modules/metrics.py official repository ran fingerprinted licence not identified · pointer only · 1fcfde9ab79b02fa · report
make_master_params andrekassis/ai-watermark/modules/attack/diffusion/fp16_util.py official repository ran no licence file found · pointer only · e20dd5102da3b050 · report
next_power_of_2 andrekassis/ai-watermark/modules/attack/diffusion/diffusion_attack.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · c9fc8e4585882848 · report
normal_kl andrekassis/ai-watermark/modules/attack/diffusion/gaussian_diffusion.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · cf2798b666b231ca · report
space_timesteps andrekassis/ai-watermark/modules/attack/diffusion/diffusion_attack.py official repository ran · fixture could not drive it no licence file found · pointer only · 9b6e4e070473e76f · report
unflatten_master_params andrekassis/ai-watermark/modules/attack/diffusion/fp16_util.py official repository ran no licence file found · pointer only · 64fff1e30802b815 · report
zero_module andrekassis/ai-watermark/modules/attack/diffusion/nn.py official repository ran · our draft was wrong no licence file found · pointer only · 129b804760b3115f · report
avg_pool_nd andrekassis/ai-watermark/modules/attack/diffusion/nn.py official repository unverified no licence file found · pointer only · ecd0fc28815b65ae · report
conv_nd andrekassis/ai-watermark/modules/attack/diffusion/nn.py official repository unverified no licence file found · pointer only · fe4eb545bbb728e0 · report
create_model andrekassis/ai-watermark/modules/attack/diffusion/diffusion_attack.py official repository unverified licence not identified · pointer only · 490304167ec39ba1 · report
load_state andrekassis/ai-watermark/modules/training.py official repository unverified licence not identified · pointer only · 7a0cdb2e58105e10 · report
resume_state andrekassis/ai-watermark/modules/training.py official repository unverified licence not identified · pointer only · 7e95e27115bf8d29 · report

Tasks

DeepFake DetectionDenoisingFace Swapping

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