SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.04653 · 2024

Hidden in the Noise: Two-Stage Robust Watermarking for Images

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 7 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2412.04653.json · badge: /api/ran/2412.04653.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Kasraarabi/Hidden-in-the-Noise canonical (classifier label)
classifier basis: census
12 ran · 4 no recorded run
FunctionStatusWhere it lives
approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
Kasraarabi/Hidden-in-the-Noise/guided_diffusion/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

backward_ddim Ran
ran, honoured the contract we drafted
Kasraarabi/Hidden-in-the-Noise/inverse_stable_diffusion.py
pointer only (licence: NONE) · get_code("b9d521d7021e46bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_to_custom_text_state_dict Ran
ran, violated the contract we drafted
Kasraarabi/Hidden-in-the-Noise/open_clip/model.py
pointer only (licence: NONE); the stored copy get_code serves, from deep-real/dcp, is pointer only (licence: NONE) · get_code("f19962ebb134b3d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
Kasraarabi/Hidden-in-the-Noise/guided_diffusion/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

forward_ddim Ran
ran, honoured the contract we drafted
Kasraarabi/Hidden-in-the-Noise/inverse_stable_diffusion.py
pointer only (licence: NONE) · get_code("3b89ab9f937dccdd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_cast_dtype Ran
ran; our contract draft was wrong, not the code
Kasraarabi/Hidden-in-the-Noise/open_clip/model.py
pointer only (licence: NONE) · get_code("dcd422d66b0581d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hf_read_jsonlines Ran
ran; our contract draft was wrong, not the code
Kasraarabi/Hidden-in-the-Noise/io_utils.py
pointer only (licence: NONE) · get_code("075fbc6126eeefe6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_jsonlines Ran
ran; our contract draft was wrong, not the code
Kasraarabi/Hidden-in-the-Noise/io_utils.py
pointer only (licence: NONE) · get_code("81cef8be4a138b63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normal_kl Ran
ran, honoured the contract we drafted
Kasraarabi/Hidden-in-the-Noise/guided_diffusion/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/agrol, is pointer only (licence: NOASSERTION) · get_code("cf2798b666b231ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prepare_inputs_for_generation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Kasraarabi/Hidden-in-the-Noise/open_clip/coca_model.py
pointer only (licence: NONE); the stored copy get_code serves, from WHU-USI3DV/TreeCLS, is pointer only (licence: NONE) · get_code("fb651d0a97fd4d3f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

register_pooler Ran
ran on a synthesized input
Kasraarabi/Hidden-in-the-Noise/open_clip/hf_model.py
pointer only (licence: NONE); the stored copy get_code serves, from WHU-USI3DV/TreeCLS, is pointer only (licence: NONE) · get_code("2a377da4a76a2d44")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resolve_globs Ran
ran; our contract draft was wrong, not the code
Kasraarabi/Hidden-in-the-Noise/io_utils.py
pointer only (licence: NONE) · get_code("afbb28c04b32db08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_model_from_openai_state_dict Not yet run
unverified (harvested, no recorded run)
Kasraarabi/Hidden-in-the-Noise/open_clip/model.py
pointer only (licence: NONE); the stored copy get_code serves, from imageomics/bioclip, is pointer only (licence: NOASSERTION) · get_code("57f1602ed20a9c21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

calculate_fid Not yet run
unverified (harvested, no recorded run)
Kasraarabi/Hidden-in-the-Noise/inpainting.py
pointer only (licence: NONE) · get_code("77b4519fb573daf7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

calculate_inception_score Not yet run
unverified (harvested, no recorded run)
Kasraarabi/Hidden-in-the-Noise/inpainting.py
pointer only (licence: NONE) · get_code("44b81851089251c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

gather_features Not yet run
unverified (harvested, no recorded run)
Kasraarabi/Hidden-in-the-Noise/open_clip/loss.py
pointer only (licence: NONE); the stored copy get_code serves, from lxa9867/imagefolder, is pointer only (licence: NOASSERTION) · get_code("ddcbd45e940484ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Kasraarabi/Hidden-in-the-Noise when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 5 the same month, 9 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
normal_kl 160 other papers
135 dated earlier, 1 the same month, 22 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
approx_standard_normal_cdf 154 other papers
129 dated earlier, 1 the same month, 22 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
109 dated earlier, 18 later, 1 same year, order not determinable · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
get_cast_dtype 66 other papers
55 dated earlier, 2 the same month, 8 later, 1 same year, order not determinable
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2210.08402 (2022-10)
LAION-5B: An open large-scale dataset for training next generation image-text models
2212.07143 (2022-12)
Reproducible scaling laws for contrastive language-image learning
and 63 more not named here
gather_features 57 other papers
50 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable · 1 only as an assembly brick
2206.01670 (2022-06)
Egocentric Video-Language Pretraining
2212.00638 (2022-12)
Finetune like you pretrain: Improved finetuning of zero-shot vision models
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
and 54 more not named here
convert_to_custom_text_state_dict 49 other papers
43 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2210.08402 (2022-10)
LAION-5B: An open large-scale dataset for training next generation image-text models
2212.07143 (2022-12)
Reproducible scaling laws for contrastive language-image learning
and 46 more not named here
register_pooler 45 other papers
39 dated earlier, 5 later, 1 same year, order not determinable
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
2302.03668 (2023-02)
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
2303.14814 (2023-03)
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
and 42 more not named here
prepare_inputs_for_generation 43 other papers
34 dated earlier, 8 later, 1 same year, order not determinable
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
2303.14814 (2023-03)
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
2305.07017 (2023-05)
An Inverse Scaling Law for CLIP Training
and 40 more not named here
build_model_from_openai_state_dict 30 other papers
24 dated earlier, 5 later, 1 same year, order not determinable
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
2302.03668 (2023-02)
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
2303.14814 (2023-03)
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
and 27 more not named here
load_jsonlines 6 other papers
6 dated earlier
2306.17194 (2023-06)
On the Exploitability of Instruction Tuning
2402.18059 (2024-02)
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
2404.04956 (2024-04)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
and 3 more not named here
backward_ddim 5 other papers
5 dated earlier
2305.20030 (2023-05)
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
2310.00076 (2023-10)
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
2404.04956 (2024-04)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
and 2 more not named here
forward_ddim 5 other papers
5 dated earlier
2305.20030 (2023-05)
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
2310.00076 (2023-10)
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
2404.04956 (2024-04)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
and 2 more not named here
hf_read_jsonlines 4 other papers
4 dated earlier
2402.18059 (2024-02)
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
2404.04956 (2024-04)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
2404.14055 (2024-04)
RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification
and 1 more not named here
resolve_globs 4 other papers
4 dated earlier
2402.18059 (2024-02)
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
2404.04956 (2024-04)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
2404.14055 (2024-04)
RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As the quality of image generators continues to improve, deepfakes become a topic of considerable societal debate. Image watermarking allows responsible model owners to detect and label their AI-generated content, which can mitigate the harm. Yet, current state-of-the-art methods in image watermarking remain vulnerable to forgery and removal attacks. This vulnerability occurs in part because watermarks distort the distribution of generated images, unintentionally revealing information about the watermarking techniques. In this work, we first demonstrate a distortion-free watermarking method for images, based on a diffusion model's initial noise. However, detecting the watermark requires comparing the initial noise reconstructed for an image to all previously used initial noises. To mitigate these issues, we propose a two-stage watermarking framework for efficient detection. During generation, we augment the initial noise with generated Fourier patterns to embed information about the group of initial noises we used. For detection, we (i) retrieve the relevant group of noises, and (ii) search within the given group for an initial noise that might match our image. This watermarking approach achieves state-of-the-art robustness to forgery and removal against a large battery of attacks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2412.04653")
get_code_for_paper("2412.04653")
have("2412.04653")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2412.04653.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2412.04653.svg)](https://syntology.ai/paper/2412.04653)

Connect an agent — have() is free.