Papers › Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

9 Dec 2024arXiv:2412.07808archive 2025-07-28

Myeongseob Ko, Henry Li, Zhun Wang, Jonathan Patsenker, Jiachen T. Wang, Qinbin Li, Ming Jin, Dawn Song, Ruoxi Jia

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns. Driven by these concerns, machine unlearning has become crucial to effectively purge undesirable knowledge from models. While existing literature has studied various unlearning techniques, these often suffer from either poor unlearning quality or degradation in text-image alignment after unlearning, due to the competitive nature of these objectives. To address these challenges, we propose a framework that seeks an optimal model update at each unlearning iteration, ensuring monotonic improvement on both objectives. We further derive the characterization of such an update. In addition, we design procedures to strategically diversify the unlearning and remaining datasets to boost performance improvement. Our evaluation demonstrates that our method effectively removes target classes from recent diffusion-based generative models and concepts from stable diffusion models while maintaining close alignment with the models' original trained states, thus outperforming state-of-the-art baselines. Our code will be made available at https://github.com/reds-lab/Restricted_gradient_diversity_unlearning.git.

PaperPDFCodeCode 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 16 code samples: 13 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 16: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (4 with no instrument failure; 6 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. 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. 9 of the 13 samples that ran have no recorded date.

reds-lab/restricted_gradient_diversity_unlearning officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 10 ran (6 instrument-failed) · 3 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

16 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 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.

4ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
2ran; the contract check could not run
3unverified

Licence: 16 of the 16 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 reds-lab/restricted_gradient_diversity_unlearning. 3 samples are listed last, in a group without a repository. “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.

reds-lab/restricted_gradient_diversity_unlearning official repository 13 samples, 10 ran (6 instrument-failed) · 3 unverified
calculate_fid_from_inception_stats in 26 papers CIFAR/fid.py ran · honoured contract fingerprinted no licence file found · pointer only · 45e941764344e7f3 · report fixture: signature mu:ndarray/1/float, sigma:ndarray/2/float, mu_ref:ndarray/1/float, sigma_ref:ndarray/2/float · returned float · level recorded, date not recorded
compute_averages in 10 papers CIFAR/compute_averages.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 97895a89ae5bdd7c · report fixture: signature input_dir:str/0/str · returned dict · level recorded 2026-09-25
file_ext in 37 papers CIFAR/dataset_tool.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a2b45afa097b55b6 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
format_time in 140 papers CIFAR/dnnlib/util.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 674eca7b9e1b6439 · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
format_time_brief in 69 papers CIFAR/dnnlib/util.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 32af001972a0699f · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
maybe_min in 36 papers CIFAR/dataset_tool.py ran · honoured contract fingerprinted no licence file found · pointer only · dd1dc700e87f36cc · report fixture: signature a:int/0/int, b:NoneType/0/? · returned int · level recorded, date not recorded
moving_average in 46 papers
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/gradient_ascent.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
parse_int_list in 59 papers CIFAR/generate.py ran · honoured contract no licence file found · pointer only · cacd4f6ec202d9b4 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
parse_tuple in 34 papers CIFAR/dataset_tool.py ran · honoured contract no licence file found · pointer only · 07b21b35ecb4815c · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-24
weight_init in 73 papers CIFAR/training/networks.py ran; the contract check could not run (RAISES) no licence file found · pointer only · d41a4250066bce93 · report fixture: signature shape:tuple/1/int, mode:str/0/str, fan_in:int/0/int, fan_out:int/0/int · returned Tensor · level recorded 2026-09-22
ablation_sampler in 17 papers CIFAR/generate.py unverified no licence file found · pointer only · 9fbf646e18eed1db · report
ask_yes_no in 70 papers CIFAR/dnnlib/util.py unverified no licence file found · pointer only · 9d31d2c4cd16bb2d · report
edm_sampler in 34 papers CIFAR/generate.py unverified no licence file found · pointer only · 8b16b0674af254db · report
Repository not located 3 samples, 3 ran (2 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
disabled_train in 172 papers repository not located ran · violated contract licence of this copy not recorded · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
sample_model in 14 papers
census: 1 implementation from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 3, kind float, dtype float32
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 15e005b12a64650d · report fixture: signature model:callable/0/?, sampler:MockSampler/0/?, c:Tensor/3/float, h:int/0/int, w:int/0/int, ddim_steps:int/0/int, scale:float/0/float, ddim_eta:float/0/float, start_code:NoneType/0/?, n_samples:int/0/int, t_start:int/0/int, log_every_t:NoneType/0/?, till_T:NoneType/0/?, verbose:bool/0/bool · returned Tensor · level recorded, date not recorded
uniform_on_device in 45 papers repository not located ran · our draft was wrong licence of this copy not recorded · d48d8354986e3b0e · report fixture: signature r1:float/0/float, r2:float/0/float, shape:tuple/1/int, device:device/0/? · returned Tensor · level recorded, date not recorded

Tasks

Image GenerationMachine Unlearning

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