Papers › UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in...
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Rao Kompella, Xiaoming Liu, Sijia Liu
The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose UnlearnCanvas, a comprehensive high-resolution stylized image dataset that facilitates the evaluation of the unlearning of artistic styles and associated objects. This dataset enables the establishment of a standardized, automated evaluation framework with 7 quantitative metrics assessing various aspects of the unlearning performance for DMs. Through extensive experiments, we benchmark 9 state-of-the-art MU methods for DMs, revealing novel insights into their strengths, weaknesses, and underlying mechanisms. Additionally, we explore challenging unlearning scenarios for DMs to evaluate worst-case performance against adversarial prompts, the unlearning of finer-scale concepts, and sequential unlearning. We hope that this study can pave the way for developing more effective, accurate, and robust DM unlearning methods, ensuring safer and more ethical applications of DMs in the future. The dataset, benchmark, and codes are publicly available at https://unlearn-canvas.netlify.app/.
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):
get_harvested_code_for_paper(arxiv_id="2402.11846")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2402.11846", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2402.11846")
Code
Syntology 74 code samples harvested from 8 repositories linked to this paper: 55 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 9 honoured, 3 violated, 12 with no contract checked; 31 where Syntology's instrument failed) · 19 unverified. Where Syntology's instrument failed: 26 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 12 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 62 samples from 7 repositories, 46 ran (17 with no instrument failure; 29 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.
No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:
- OPTML-Group/Unlearn-Saliency, found in paper text by Syntology: Syntology's graph links these samples to SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image... (arXiv:2310.12508; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified) and Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement (arXiv:2409.19732; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method.
- rohitgandikota/erasing, found in paper text by Syntology: Syntology's graph links these samples to Erasing Concepts from Diffusion Models (arXiv:2303.07345; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified) and Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image... (arXiv:2402.05375; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 8 of the 55 samples that ran have no recorded date.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
74 samples harvested: 55 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 9 honoured, 3 violated, 12 with no contract checked; 31 where Syntology's instrument failed) · 19 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.
Licence: 40 of the 74 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 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 8 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
4b1e44a59b2094f3 · report
fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-24 5c07965b9fb3ae74 · report
fixture: signature x:Image/0/? · returned Tensor · level recorded 2026-09-24 c7a8a88e04fd5351 · report
fixture: signature n:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-24 7064fad2ca846b74 · report
fixture: signature n:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, rho:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-24 b22174509b22ebfe · report
fixture: signature examples:dict/0/?, transform:callable/0/?, image_key:str/0/str, mode:str/0/str · returned dict · level recorded 2026-09-24 b1368330cf0f5642 · report
fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24 d72762b700feee6f · report
fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24 census: 8 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket diffusion_model_finetuning/evaluation/fid.py ran · honoured contract fingerprinted no licence file found · pointer only ·
b4318fcc73fe317f · report
fixture: signature elements:Tensor/2/float · returned Tensor · level recorded 2026-09-24 ca508754772590c4 · report
fixture: signature x:Tensor/4/float · returned Image · level recorded 2026-09-24 f2517e59a9ce2ce4 · report
1226d62dd93f8b5f · report
f9bd2e83191afad1 · report
067f451b2dbf739d · report
fixture: signature image_path:str/0/str, left:int/0/int, right:int/0/int, top:int/0/int, bottom:int/0/int · returned ndarray · level recorded, date not recorded f3e6737ebc70cbbf · report
fixture: signature attention_store:AttentionStore/0/?, res:int/0/int, from_where:list/1/str, is_cross:bool/0/bool, select:int/0/int · returned Tensor · level recorded, date not recorded 6d190d192ff5e777 · report
fixture: signature model:callable/0/?, controller:StandInController/0/?, latents:Tensor/2/float, context:list/1/Tensor, t:Tensor/1/int, guidance_scale:float/0/float, low_resource:bool/0/bool · returned Tensor · level recorded 2026-09-24 e3c3bb87bbe9b4a7 · report
fixture: signature vae:callable/0/?, latents:Tensor/4/float · returned ndarray · level recorded, date not recorded 85d5eb123674597d · report
fixture: signature image:ndarray/3/int, text:str/0/str, text_color:tuple/1/int · returned ndarray · level recorded 2026-09-24 c771ff3009ac78c7 · report
f1eec059eb235348 · report
019f2139ed0982c1 · report
8295ffcdfbfbcb67 · report
254211bc4b378fe4 · report
fixture: signature image:Image/0/? · returned Image · level recorded 2026-09-22 8241c0562bc710fd · report
fixture: signature it:list/1/int, size:int/0/int · returned callable_iterator · level recorded, date not recorded 2cb4375648881b05 · report
fixture: signature images:list/1/str, model:callable/0/?, device:str/0/str, batch_size:int/0/int, num_workers:int/0/int · returned ndarray · level recorded 2026-09-24 489a35aa27273ede · report
fixture: signature caption_target:str/0/str, caption:str/0/str · returned str · level recorded 2026-09-24 ea4a1969281507a5 · report
fixture: signature path:str/0/str · returned bool · level recorded 2026-09-22 11ec361f7a77d02c · report
fixture: signature img:Image/0/? · returned JpegImageFile · level recorded 2026-09-22 census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket compvis/src/utils.py ran MIT (permissive) ·
f7c1195d335ba6ea · report
fixture: signature data:list/1/tuple, model:callable/0/?, sampler:MinimalSampler/0/?, outpath:str/0/str, ddim_steps:int/0/int, n_samples:int/0/int, ddim_eta:float/0/float, n_iter:int/0/int, scale:float/0/float, batch_size:int/0/int, shape:tuple/1/int, fixed_code:bool/0/bool, device:str/0/str, skip_save:bool/0/bool, skip_grid:bool/0/bool, metadata:bool/0/bool, base_count:int/0/int, n_rows:int/0/int, wandb_log:bool/0/bool, ckptname:str/0/str, rank:NoneType/0/? · returned tuple · level recorded 2026-09-24 9b4052692da3a8bc · report
fixture: signature z_i:ndarray/1/float, z_j:ndarray/1/float · returned ndarray · level recorded 2026-09-24 894009c45bf51dcf · report
fixture: signature embeddings:ndarray/2/float, S:list/1/tuple · returned ndarray · level recorded 2026-09-24 census: 7 implementations from 9 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 evalscripts/styleloss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only ·
1090950b58e9358b · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 9ad49e53202d0110 · report
fixture: signature image_name:str/0/str · returned Tensor · level recorded 2026-09-26 56e74fc4361256b9 · report
fixture: signature image_name:str/0/str · returned Tensor · level recorded 2026-09-24 8517a5a2a142c0ca · report
fixture: signature l:list/1/str · returned list · level recorded 2026-09-24 f53d21f5e97513c9 · report
fixture: signature prompt_tokens:Tensor/2/int, prompt_embeds:Tensor/3/float, erased_prompt_tokens:Tensor/2/int, erased_prompt_embeds:Tensor/3/float, matching_metric:str/0/str, special_token_ids:set/0/?, weight_dtype:dtype/0/? · returned Tensor · level recorded 2026-09-24 cb0d0aa60feeb917 · report
fixture: signature target:Tensor/1/float · returned Tensor · level recorded 2026-09-24 f0e2148d0a7aa2a2 · report
fixture: signature cfg_path:str/0/str · returned GenerationConfig · level recorded 2026-09-24 299ce035eef45373 · report
fixture: signature safetensors_file:str/0/str · returned dict · level recorded 2026-09-24 9e90320bd677ef48 · report
fixture: signature path:str/0/str · returned list · level recorded 2026-09-24 1f3069e15698ab71 · report
fixture: signature path:PosixPath/0/? · returned list · level recorded 2026-09-24 3c4f9becca932b96 · report
fixture: signature models:list/1/str, ratios:list/1/float, merge_dtype:dtype/0/? · returned dict · level recorded 2026-09-24 f4e5ea8e5d469b27 · report
fixture: signature extra_args:list/1/str · returned dict · level recorded 2026-09-24 ca142e6d863ef6a6 · report
fixture: signature precision:str/0/str · returned dtype · level recorded 2026-09-24 98dc0093af97db19 · report
b8e710925cbb4290 · report
e5dbb0469de3dff9 · report
fixture: signature examples:list/1/dict, with_prior_preservation:bool/0/bool · returned dict · level recorded 2026-09-24 74e4f1bd2e3487ff · report
fixture: signature safeloras:MockSafetensors/0/? · returned dict · level recorded 2026-09-24 4ed7a5bbe748cb10 · report
fixture: signature train_dataset:MinimalDataset/0/?, train_batch_size:int/0/int, tokenizer:MinimalTokenizer/0/?, vae:callable/0/?, text_encoder:callable/0/? · returned DataLoader · level recorded 2026-09-24 1f5610eafe95d0c8 · report
2f00b39db5a81466 · report
29136f2953d790e8 · report
fixture: signature path:str/0/str, data_type:str/0/str, img_size:int/0/int, batch_size:int/0/int · returned DataLoader · level recorded 2026-09-24 2ccf562d07794d65 · report
fixture: signature net:callable/0/? · returned list · level recorded 2026-09-24 census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64 ddpm/models/diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only ·
cb49209c125de1b4 · report
fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded, date not recorded census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 1, kind float, dtype float64 sd/train_scripts/erasediff.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
f398bc270e4f4ffe · report
fixture: signature a:ndarray/1/float, n:int/0/int · returned ndarray · level recorded 2026-09-22 36a45cceb1209d2f · report
fixture: signature model:callable/0/?, x0:Tensor/4/float, t:Tensor/1/int, e:Tensor/4/float, b:Tensor/1/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24 ca8a1bf21579d253 · report
fixture: signature model:callable/0/?, x0:Tensor/4/float, t:Tensor/1/int, c:Tensor/1/int, e:Tensor/4/float, b:Tensor/1/float, cond_drop_prob:float/0/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24 census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 ddpm/models/diffusion.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
3137073275f8c21a · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded 3c6433dd421724e0 · report
fixture: signature shape:tuple/1/int, prob:float/0/float, device:device/0/? · returned Tensor · level recorded 2026-09-22 0bae0d076b1ae674 · report
fixture: signature folder_path:str/0/str · returned ndarray · level recorded 2026-09-24 8168d4d8419b92c3 · report
fixture: signature net:callable/0/?, old_param:list/1/Tensor · returned SimpleNet · level recorded 2026-09-24 d278a27b738c2136 · report
d9def42110729a85 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded 160bb14bd76201b4 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded cadb98df0b43c793 · report
fixture: signature obj:dict/0/? · returned bytes · level recorded 2026-09-24 c7ae957080f6f740 · report
fixture: signature data:dict/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22 2bc7277fbb33cc3f · report
fixture: signature buf:bytes/0/? · returned dict · level recorded 2026-09-26 51738010a21f76a1 · report
fixture: signature path:str/0/str · returned bytes · level recorded 2026-09-25 9ea29973ea0485a1 · report
361b798104c4eff0 · report
0f58d86ba1ef71e6 · report
50eeb60cc0488d27 · report
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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