Papers › Training-Free Watermarking for Autoregressive Image Generation

Training-Free Watermarking for Autoregressive Image Generation

20 May 2025arXiv:2505.14673archive 2025-07-28

Yu tong, Zihao Pan, Shuai Yang, Kaiyang Zhou

Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored. We propose IndexMark, a training-free watermarking framework for autoregressive image generation models. IndexMark is inspired by the redundancy property of the codebook: replacing autoregressively generated indices with similar indices produces negligible visual differences. The core component in IndexMark is a simple yet effective match-then-replace method, which carefully selects watermark tokens from the codebook based on token similarity, and promotes the use of watermark tokens through token replacement, thereby embedding the watermark without affecting the image quality. Watermark verification is achieved by calculating the proportion of watermark tokens in generated images, with precision further improved by an Index Encoder. Furthermore, we introduce an auxiliary validation scheme to enhance robustness against cropping attacks. Experiments demonstrate that IndexMark achieves state-of-the-art performance in terms of image quality and verification accuracy, and exhibits robustness against various perturbations, including cropping, noises, Gaussian blur, random erasing, color jittering, and JPEG compression.

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="2505.14673")

Code

Syntology Ran 2 of 19 code samples harvested from 1 repository linked to this paper; 17 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: official repository: 19 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.

maifoundations/indexmark officialmentioned in papermentioned on GitHubpytorchMIT 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; 2 ran; 2 honoured the contract we drafted; 17 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
17unverified

Licence: 0 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 maifoundations/indexmark. “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.

find_multiple maifoundations/indexmark/autoregressive/models/gpt.py official repository ran · honoured contract fingerprinted MIT (permissive) · f6ff7671338c9c92 · report
precompute_freqs_cis_2d maifoundations/indexmark/autoregressive/models/gpt.py official repository ran · honoured contract MIT (permissive) · 7f53b2cdcd16fad9 · report
build_imagenet maifoundations/indexmark/dataset/imagenet.py official repository unverified MIT (permissive) · 5cceaa9d0edbce06 · report
build_imagenet_code maifoundations/indexmark/dataset/imagenet.py official repository unverified MIT (permissive) · b6635606f35f6a1a · report
collate_fn maifoundations/indexmark/Index_encoder/ft2_2loss.py official repository unverified MIT (permissive) · 9780feca2753ce85 · report
green_check maifoundations/indexmark/attack_val.py official repository unverified MIT (permissive) · f4971cc46e80bbe7 · report
image_distortion maifoundations/indexmark/attack_val.py official repository unverified MIT (permissive) · 392c601621077a9c · report
load_image_to_tensor maifoundations/indexmark/Index_encoder/preprocess_for_finetuning_zq.py official repository unverified MIT (permissive) · 013417e3304262ee · report
load_image_to_tensor maifoundations/indexmark/verification.py official repository unverified MIT (permissive) · 52d6aa62b8ee01d3 · report
load_pil_image_to_tensor maifoundations/indexmark/attack_val.py official repository unverified MIT (permissive) · 551428d47bce5e23 · report
load_prompts_from_csv maifoundations/indexmark/generation.py official repository unverified MIT (permissive) · 4a1df45063de3ec2 · report
logits_to_probs maifoundations/indexmark/autoregressive/models/generate.py official repository unverified MIT (permissive) · 9dac59261197935f · report
mscocojson2list maifoundations/indexmark/generation.py official repository unverified MIT (permissive) · ebbba64af32405e0 · report
precompute_freqs_cis maifoundations/indexmark/autoregressive/models/gpt.py official repository unverified MIT (permissive) · 0f0ff4e443413018 · report
sample maifoundations/indexmark/autoregressive/models/generate.py official repository unverified MIT (permissive) · de8908ac0f302419 · report
sample maifoundations/indexmark/autoregressive/models/generatearcon.py official repository unverified MIT (permissive) · a3052bf4fc15d6da · report
top_k_top_p_filtering maifoundations/indexmark/autoregressive/models/generate.py official repository unverified MIT (permissive) · f2fea48028c7ae80 · report
vectorized_replacement_process maifoundations/indexmark/generation.py official repository unverified MIT (permissive) · 72fe1f0d7fd26e7b · report
vectorized_replacement_process maifoundations/indexmark/generation_c2i.py official repository unverified MIT (permissive) · 723170b20751a59f · report

Tasks

Image Generation

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