SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2511.01307 · NeurIPS · 2025

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

Jong Ko, Gyeong-Moon Park, Tae-Young Lee, Juwon Seo

arXiv · PDF · Open in the Atlas

Code that ran

9 of 16 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 7 no recorded run), measured 2026-11-22; 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/2511.01307.json · badge: /api/ran/2511.01307.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
KU-VGI/APDM canonical (classifier label)
classifier basis: census
9 ran · 7 no recorded run
FunctionStatusWhere it lives
cal_fid Ran
ran, honoured the contract we drafted
KU-VGI/APDM/evaluation/fid.py
pointer only (licence: NONE) · get_code("56eabe5c1bd59ac3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

calculate_statistics Ran
ran; our contract draft was wrong, not the code
KU-VGI/APDM/evaluation/fid.py
pointer only (licence: NONE) · get_code("93b8fbfaaf3d24e6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

check_exp Ran
ran; our contract draft was wrong, not the code
KU-VGI/APDM/gen_arguments.py
pointer only (licence: NONE) · get_code("79bde245ed8e1d95")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

encode_prompt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KU-VGI/APDM/protect.py
pointer only (licence: NONE) · get_code("24a0be604862ac52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

extract_features Ran
ran, honoured the contract we drafted
KU-VGI/APDM/evaluation/fid.py
pointer only (licence: NONE) · get_code("6ecd3c07d559c10c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

get_arguments_eval Ran
ran; our contract draft was wrong, not the code
KU-VGI/APDM/gen_arguments.py
pointer only (licence: NONE) · get_code("30c93f2d9877816f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

load_prompt_list Ran
ran; our contract draft was wrong, not the code
KU-VGI/APDM/evaluation/personalized_sampler.py
pointer only (licence: NONE) · get_code("a15239baf1896d01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

pil_to_tensor Ran
ran, honoured the contract we drafted
KU-VGI/APDM/evaluation/dino.py
pointer only (licence: NONE) · get_code("49d329492296a105")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

tensor2pil Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KU-VGI/APDM/evaluation/clip_score.py
pointer only (licence: NONE); the stored copy get_code serves, from mingukkang/gigagan, is pointer only (licence: NONE) · get_code("11687d1d3ed1d3db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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.

calculate_dino Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/evaluation/dino.py
pointer only (licence: NONE) · get_code("e675e003c0de1980")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

calculate_dino Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/evaluation/dino_use.py
pointer only (licence: NONE) · get_code("c1f43c65d8e28cef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

get_arguments Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/gen_arguments.py
pointer only (licence: NONE) · get_code("24839e38b640f364")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

import_model_class_from_model_name_or_path Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/train_dreambooth.py
pointer only (licence: NONE) · get_code("0eb3e94e8635150e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

parse_args Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/evaluate.py
pointer only (licence: NONE) · get_code("23e8ac6df39d00e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

parse_args Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/evaluate_bre.py
pointer only (licence: NONE) · get_code("0fb308e47bcfb38d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

parse_args Not yet run
unverified (harvested, no recorded run)
KU-VGI/APDM/evaluate_db.py
pointer only (licence: NONE) · get_code("af2461a066b4adee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KU-VGI/APDM 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. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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
import_model_class_from_model_name_or_path 13 other papers
13 dated earlier
2305.19327 (2023-05)
Cones 2: Customizable Image Synthesis with Multiple Subjects
2307.06949 (2023-07)
HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models
2311.18815 (2023-11)
IMMA: Immunizing text-to-image Models against Malicious Adaptation
and 10 more not named here
calculate_statistics 1 other paper
1 dated earlier
2405.09879 (2024-05)
Generative Unlearning for Any Identity
tensor2pil 1 other paper
1 dated earlier
2406.01561 (2024-06)
Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

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

Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks, as personalization techniques can be misused by malicious users to generate unauthorized content. Although several studies have attempted to counter this by generating adversarially perturbed samples designed to disrupt personalization, they rely on unrealistic assumptions and become ineffective in the presence of even a few clean images or under simple image transformations. To address these challenges, we shift the protection target from the images to the diffusion model itself to hinder the personalization of specific subjects, through our novel framework called Anti-Personalized Diffusion Models (APDM). We first provide a theoretical analysis demonstrating that a naive approach of existing loss functions to diffusion models is inherently incapable of ensuring convergence for robust anti-personalization. Motivated by this finding, we introduce Direct Protective Optimization (DPO), a novel loss function that effectively disrupts subject personalization in the target model without compromising generative quality. Moreover, we propose a new dual-path optimization strategy, coined Learning to Protect (L2P). By alternating between personalization and protection paths, L2P simulates future personalization trajectories and adaptively reinforces protection at each step. Experimental results demonstrate that our framework outperforms existing methods, achieving state-of-the-art performance in preventing unauthorized personalization. The code is available at https://github.com/KU-VGI/APDM.

For agents

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

get_harvested_code_for_paper("2511.01307")
get_code_for_paper("2511.01307")
have("2511.01307")

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

curl https://syntology.ai/api/ran/2511.01307.json

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

[![Syntology run record](https://syntology.ai/api/ran/2511.01307.svg)](https://syntology.ai/paper/2511.01307)

Connect an agent — have() is free.