SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.00875 · NeurIPS · 2022

Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

Shu-Tao Xia, Bo Li, Yiming Li, Yong Jiang, Yong Yang, Yang Bai

arXiv · PDF · Open in the Atlas

Code that ran

3 of 10 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 7 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/2210.00875.json · badge: /api/ran/2210.00875.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
THUYimingLi/Untargeted_Backdoor_Watermark canonical (classifier label)
classifier basis not recorded on the link
3 ran · 7 no recorded run
FunctionStatusWhere it lives
ResNet18 Ran
ran; our contract draft was wrong, not the code
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/model_i.py
code served (permissive licence) · get_code("3250979a4f8eac8e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ResNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gen_grid Ran
ran, honoured the contract we drafted
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-P/train_UBW_P_WaNet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from 20000yshust/Backdoor-Defense-Via-Suppressing-Model-Shortcuts, is pointer only (licence: NONE) · get_code("afc9001040d3aa34")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from 20000yshust/Backdoor-Defense-Via-Suppressing-Model-Shortcuts, and GitHub detected no licence in that repository 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.

make_layers Ran
ran; our contract draft was wrong, not the code
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/model.py
code served (permissive licence) · get_code("ac62432dc5134b0d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function takes two parameters: cfg and batch_norm
# cfg should be a list/sequence of either integers (channel counts) or 'M' (maxpool marker)
# batch_norm is a boolean flag

# Using one of the predefined configurations from the module-level cfg dict
cfg_list = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M']

ARGS = {
    'cfg': cfg_list,
    'batch_norm': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Dloss_s Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-P/eval_UBW_P_BadNets.py
code served (permissive licence) · get_code("6fe7f1dde4b402c6")
How it ran

no invocation recorded.

ResNet18 Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/model.py
code served (permissive licence) · get_code("febb3deba6c74f90")
How it ran

no invocation recorded.

patch_source Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/eval_loss.py
code served (permissive licence) · get_code("36c28aa12c9937f6")
How it ran

no invocation recorded.

patch_source Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-P/eval_UBW_P_BadNets.py
code served (permissive licence) · get_code("766315d0cde3c1dc")
How it ran

no invocation recorded.

patch_source Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/eval_ASR.py
code served (permissive licence) · get_code("26a12cb0a49b0d7e")
How it ran

no invocation recorded.

prepare_datasets Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/eval_loss.py
code served (permissive licence) · get_code("46fc2d22eb1e47be")
How it ran

no invocation recorded.

prepare_datasets Not yet run
unverified (harvested, no recorded run)
THUYimingLi/Untargeted_Backdoor_Watermark/UBW-C/eval_ASR.py
code served (permissive licence) · get_code("5ba9825ab6ff7eca")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 later) and 5 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
make_layers 59 other papers
35 dated earlier, 23 later, 1 same year, order not determinable
1411.4038 (2014-11)
Fully Convolutional Networks for Semantic Segmentation
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1511.05950 (2015-11)
Staleness-aware Async-SGD for Distributed Deep Learning
and 56 more not named here
ResNet18 11 other papers
2 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable
1911.00068 (2019-11)
Confident Learning: Estimating Uncertainty in Dataset Labels
2008.00627 (2020-08)
Learning to Purify Noisy Labels via Meta Soft Label Corrector
136850512 (2022 (year only))
Rethinking Confidence Calibration for Failure Prediction
and 8 more not named here
gen_grid 2 other papers
2 later
2211.05631 (2022-11)
Backdoor Defense via Suppressing Model Shortcuts
2302.01762 (2023-02)
BackdoorBox: A Python Toolbox for Backdoor Learning

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

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily evaluate and improve their learning methods. Since the data collection is usually time-consuming or even expensive, how to protect their copyrights is of great significance and worth further exploration. In this paper, we revisit dataset ownership verification. We find that existing verification methods introduced new security risks in DNNs trained on the protected dataset, due to the targeted nature of poison-only backdoor watermarks. To alleviate this problem, in this work, we explore the untargeted backdoor watermarking scheme, where the abnormal model behaviors are not deterministic. Specifically, we introduce two dispersibilities and prove their correlation, based on which we design the untargeted backdoor watermark under both poisoned-label and clean-label settings. We also discuss how to use the proposed untargeted backdoor watermark for dataset ownership verification. Experiments on benchmark datasets verify the effectiveness of our methods and their resistance to existing backdoor defenses. Our codes are available at https://github.com/THUYimingLi/Untargeted_Backdoor_Watermark.

For agents

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

get_harvested_code_for_paper("2210.00875")
get_code_for_paper("2210.00875")
have("2210.00875")

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

curl https://syntology.ai/api/ran/2210.00875.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.00875.svg)](https://syntology.ai/paper/2210.00875)

Connect an agent — have() is free.