Papers › Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

7 Oct 2023arXiv:2310.04687archive 2025-07-28

BoYang Zheng, Chumeng Liang, Xiaoyu Wu

Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized diffusion customization, by adding protective watermarks to images and poisoning diffusion models. However, current protection, leveraging untargeted attacks, does not appear to be effective enough. In this paper, we propose a simple yet effective improvement for the protection against unauthorized diffusion customization by introducing targeted attacks. We show that by carefully selecting the target, targeted attacks significantly outperform untargeted attacks in poisoning diffusion models and degrading the customization image quality. Extensive experiments validate the superiority of our method on two mainstream customization methods of diffusion models, compared to existing protections. To explain the surprising success of targeted attacks, we delve into the mechanism of attack-based protections and propose a hypothesis based on our observation, which enhances the comprehension of attack-based protections. To the best of our knowledge, we are the first to both reveal the vulnerability of diffusion models to targeted attacks and leverage targeted attacks to enhance protection against unauthorized diffusion customization. Our code is available on GitHub: \url{https://github.com/psyker-team/mist-v2}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.04687")

Code

Syntology Ran 14 of 24 code samples harvested from 3 repositories linked to this paper; 10 have no recorded run. Of those that ran: 2 ran · violated contract; 2 ran · our draft was wrong; 10 ran with no contract checked.

By repository: official repository: 22 samples from 2 repositories, 13 ran; community: 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

psyker-team/mist-v2 officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
caradryanliang/improvedadvdm officialmentioned in paperpytorch 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

24 samples harvested; 14 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
2ran · our draft was wrong
10ran
10unverified

Licence: 14 of the 24 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

attack_forward caradryanliang/improvedadvdm/benchmarks/photoguard+.py official repository ran no licence file found · pointer only · 79482e8ecae87aaa · report
default psyker-team/mist-v2/ldm/modules/attention.py official repository ran · violated contract Apache-2.0 (permissive) · 424012cb37b31172 · report
eval_step caradryanliang/improvedadvdm/evaluation.py official repository ran no licence file found · pointer only · 7f5f265e8a1e513c · report
exists psyker-team/mist-v2/ldm/modules/attention.py official repository ran · violated contract Apache-2.0 (permissive) · aa5486a3650902d8 · report
get_images_from_path caradryanliang/improvedadvdm/evaluation.py official repository ran no licence file found · pointer only · 06e4ea094029c19d · report
get_images_from_path caradryanliang/improvedadvdm/i2i.py official repository ran no licence file found · pointer only · 1a71962efc4d5ae4 · report
inpainting_dataloader psyker-team/mist-v2/lora_diffusion/cli_lora_pti.py official repository ran Apache-2.0 (permissive) · d793962f13865771 · report
ismap psyker-team/mist-v2/ldm/util.py official repository ran Apache-2.0 (permissive) · d72762b700feee6f · report
load_data caradryanliang/improvedadvdm/attacks/aspl_lora.py official repository ran no licence file found · pointer only · 686a5a7fc55acb4e · report
load_data psyker-team/mist-v2/attacks/mist.py official repository ran Apache-2.0 (permissive) · a3135d69d30aaba2 · report
text2img_dataloader psyker-team/mist-v2/lora_diffusion/cli_lora_pti.py official repository ran Apache-2.0 (permissive) · aa63f591fb2e9bd7 · report
transform_to_tensor caradryanliang/improvedadvdm/evaluation.py official repository ran no licence file found · pointer only · cd576e2f55b71b75 · report
uniq psyker-team/mist-v2/ldm/modules/attention.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 9a299fe5ae09e407 · report
autocast psyker-team/mist-v2/ldm/util.py official repository unverified Apache-2.0 (permissive) · 32af1c12fd826ef2 · report
compute_grad caradryanliang/improvedadvdm/benchmarks/photoguard+.py official repository unverified no licence file found · pointer only · 93c799084cc33809 · report
import_model_class_from_model_name_or_path caradryanliang/improvedadvdm/attacks/aspl_lora.py official repository unverified no licence file found · pointer only · 2f00b39db5a81466 · report
log_txt_as_img psyker-team/mist-v2/ldm/util.py official repository unverified Apache-2.0 (permissive) · f9bd2e83191afad1 · report
parse_args caradryanliang/improvedadvdm/attacks/aspl_lora.py official repository unverified no licence file found · pointer only · 9bd2fe7bf5cdf878 · report
parse_args caradryanliang/improvedadvdm/attacks/aspl_lora_m.py official repository unverified no licence file found · pointer only · 65aaa57a4aeee3ff · report
parse_args caradryanliang/improvedadvdm/attacks/target_antidb.py official repository unverified no licence file found · pointer only · fd7f8599a9b1bb7d · report
parse_args caradryanliang/improvedadvdm/benchmarks/advdm.py official repository unverified no licence file found · pointer only · a12d53df966bda20 · report
parse_args psyker-team/mist-v2/attacks/mist.py official repository unverified Apache-2.0 (permissive) · a56c4df534ae4170 · report
collate_fn vinairesearch/anti-dreambooth/train_dreambooth.py community ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · 229d634611bdc645 · report
parse_args vinairesearch/anti-dreambooth/train_dreambooth.py community unverified AGPL-3.0 (copyleft) · pointer only · 573f16fb8e34edf6 · report

Tasks

Adversarial AttackImage GenerationMisinformation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionLatent Diffusion Model

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