Papers › VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

12 Jun 2023NeurIPS 2023 11arXiv:2306.06874archive 2025-07-28

Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image conditional generation. However, recent studies have shown that basic unconditional DMs (e.g., DDPM and DDIM) are vulnerable to backdoor injection, a type of output manipulation attack triggered by a maliciously embedded pattern at model input. This paper presents a unified backdoor attack framework (VillanDiffusion) to expand the current scope of backdoor analysis for DMs. Our framework covers mainstream unconditional and conditional DMs (denoising-based and score-based) and various training-free samplers for holistic evaluations. Experiments show that our unified framework facilitates the backdoor analysis of different DM configurations and provides new insights into caption-based backdoor attacks on DMs. Our code is available on GitHub: https://github.com/IBM/villandiffusion

PaperPDFConference PDFCodeCode 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 14 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 9 samples that ran have no recorded date.

ibm/villandiffusion officialmentioned in paperpytorchApache-2.0Syntology: 14 samples, 9 ran (2 instrument-failed) · 5 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

14 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

3ran · honoured contract
2ran · violated contract
2ran · our draft was wrong
2ran
5unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ibm/villandiffusion. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ibm/villandiffusion official repository 14 samples, 9 ran (2 instrument-failed) · 5 unverified
Upsample in 77 papers model.py ran · our draft was wrong Apache-2.0 (permissive) · 8bee9b7a4832d4a1 · report fixture: returned ConvTranspose2d · level recorded 2026-09-22
action_generator config.py ran Apache-2.0 (permissive) · 7eef736dc758d990 · report fixture: signature default_action:bool/0/bool · returned str · level recorded 2026-09-25
cosine_beta_schedule in 76 papers loss.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f3a9cdb81c13d825 · report fixture: signature timesteps:int/0/int, s:float/0/float · returned Tensor · level recorded 2026-09-24
default in 430 papers model.py ran · violated contract Apache-2.0 (permissive) · fbf9ec7be545688e · report fixture: signature val:NoneType/0/?, d:str/0/str · returned str · level recorded 2026-09-22
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
model.py ran · violated contract Apache-2.0 (permissive) · 608e364a9d2376a3 · report fixture: signature x:Tensor/1/int · returned bool · level recorded, date not recorded
linear_beta_schedule in 42 papers loss.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 37a36e71b86103ce · report fixture: signature timesteps:int/0/int · returned Tensor · level recorded 2026-09-22
quadratic_beta_schedule in 9 papers loss.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 496165266c2eceff · report fixture: signature timesteps:int/0/int · returned Tensor · level recorded 2026-09-24
read_json in 250 papers VillanDiffusion.py ran · our draft was wrong Apache-2.0 (permissive) · 410e560ea7b3decb · report fixture: signature args:Namespace/0/?, file:str/0/str · returned dict · level recorded, date not recorded
yield_default arg_parser.py ran Apache-2.0 (permissive) · 5a5ee8bd0dc9da41 · report fixture: signature config:TestConfig/0/?, return_dict:bool/0/bool · returned DummyClass · level recorded 2026-09-25
calculate_activation_statistics in 75 papers fid_score.py unverified Apache-2.0 (permissive) · a17aa1b06ec919e8 · report
calculate_frechet_distance in 119 papers fid_score.py unverified Apache-2.0 (permissive) · 0def50a351111624 · report
download_img caption_dataset.py unverified Apache-2.0 (permissive) · be5b84142037dc3b · report
get_activations in 100 papers fid_score.py unverified Apache-2.0 (permissive) · 9f5980b8530c7409 · report
import_model_class_from_model_name_or_path in 64 papers caption_sim.py unverified Apache-2.0 (permissive) · 2f00b39db5a81466 · report

Tasks

Backdoor AttackDenoising

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