Papers › SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models

SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models

19 Apr 2024arXiv:2404.12699archive 2025-07-28

Jiangyi Deng, Shengyuan Pang, Yanjiao Chen, Liangming Xia, Yijie Bai, Haiqin Weng, Wenyuan Xu

Instead of building deep learning models from scratch, developers are more and more relying on adapting pre-trained models to their customized tasks. However, powerful pre-trained models may be misused for unethical or illegal tasks, e.g., privacy inference and unsafe content generation. In this paper, we introduce a pioneering learning paradigm, non-fine-tunable learning, which prevents the pre-trained model from being fine-tuned to indecent tasks while preserving its performance on the original task. To fulfill this goal, we propose SOPHON, a protection framework that reinforces a given pre-trained model to be resistant to being fine-tuned in pre-defined restricted domains. Nonetheless, this is challenging due to a diversity of complicated fine-tuning strategies that may be adopted by adversaries. Inspired by model-agnostic meta-learning, we overcome this difficulty by designing sophisticated fine-tuning simulation and fine-tuning evaluation algorithms. In addition, we carefully design the optimization process to entrap the pre-trained model within a hard-to-escape local optimum regarding restricted domains. We have conducted extensive experiments on two deep learning modes (classification and generation), seven restricted domains, and six model architectures to verify the effectiveness of SOPHON. Experiment results verify that fine-tuning SOPHON-protected models incurs an overhead comparable to or even greater than training from scratch. Furthermore, we confirm the robustness of SOPHON to three fine-tuning methods, five optimizers, various learning rates and batch sizes. SOPHON may help boost further investigations into safe and responsible AI.

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 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (4 with no instrument failure; 5 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chiange/sophon officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 9 ran (5 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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 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.

5ran · our draft was wrong
4ran
3unverified

Licence: 12 of the 12 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 chiange/sophon. “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.

chiange/sophon official repository 12 samples, 9 ran (5 instrument-failed) · 3 unverified
build_training_mode generation/utils.py ran no licence file found · pointer only · fff1ecce262e106d · report fixture: signature config:Config/0/?, model:callable/0/? · returned tuple · level recorded 2026-09-24
compute_beta_schedule generation/generateimg.py ran no licence file found · pointer only · 629fc73f4a30794c · report fixture: signature beta_schedule_mode:str/0/str, t:int/0/int, linear_beta_1:float/0/float, linear_beta_t:float/0/float, cosine_s:float/0/float · returned Tensor · level recorded 2026-09-24
extract in 149 papers
census: 9 implementations from 12 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
generation/generateimg.py ran no licence file found · pointer only · 99ef51bcd86d43ff · report fixture: signature v:Tensor/1/float, t:Tensor/1/int, x_shape:tuple/1/int · returned Tensor · level recorded 2026-09-24
get_logger in 383 papers generation/utils.py ran · our draft was wrong no licence file found · pointer only · 7afc765004593554 · report fixture: signature name:str/0/str, log_dir:str/0/str · returned Logger · level recorded 2026-09-24
one_hot_to_value classification/utils.py ran · our draft was wrong no licence file found · pointer only · 87e6da0fde7c373b · report fixture: returned int · level recorded 2026-09-24
resnet18 in 432 papers classification/model.py ran · our draft was wrong no licence file found · pointer only · 72573fa9342b93d8 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers classification/model.py ran · our draft was wrong no licence file found · pointer only · a2e264debc209e26 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet50 in 121 papers classification/model.py ran · our draft was wrong no licence file found · pointer only · 6de37431d3b97f85 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
test_accuracy in 6 papers classification/utils.py ran no licence file found · pointer only · 30e09076ea1f6a73 · report fixture: signature model:callable/0/?, test_loader:MinimalDataLoader/0/? · returned tuple · level recorded 2026-09-24
all_reduce_operation_in_group_for_variables generation/train_diffusion_model.py unverified no licence file found · pointer only · 51ae3e764bac1f5d · report
fast_adapt generation/combined_denoise_maml_diffusion_celeba.py unverified no licence file found · pointer only · f67260090083a68f · report
train_diffusion_model generation/train_diffusion_model.py unverified no licence file found · pointer only · 2a75c6d9c3a0e446 · report

Tasks

Meta-Learning

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